© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33499
    Prev
    Next
    INDEX
    Explanations

    information related to public debates and discussions on various topics, particularly with a focus on specific issues and perspectives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    637
    +0.11
    0.5%
    479
    +0.10
    0.5%
    23
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.11
    0.11
    339
    +0.10
    0.07
    22
    +0.10
    0.09
    Negative Logits
    viation
    -0.72
    rers
    -0.72
    istas
    -0.68
    iov
    -0.67
    stretched
    -0.67
    tis
    -0.66
    oise
    -0.66
    osc
    -0.66
    isin
    -0.65
    gery
    -0.65
    POSITIVE LOGITS
     HuffPost
    0.89
     VIDEOS
    0.88
     Expand
    0.77
     STOR
    0.76
    VERTISEMENT
    0.73
     roundup
    0.73
     Forbes
    0.72
     TOP
    0.71
    Feature
    0.71
     Stories
    0.70
    Activations Density 6.445%

    No Known Activations