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

    Neuronpedia

    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. 39661
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases signifying movement or progression, often within a narrative context

    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
    447
    +0.24
    1.3%
    756
    +0.12
    0.7%
    288
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.24
    -0.14
    86
    +0.12
    0.06
    554
    +0.08
    -0.11
    Negative Logits
    rip
    -0.63
    OME
    -0.55
    knife
    -0.55
    tein
    -0.53
    icion
    -0.51
    gart
    -0.51
    oleon
    -0.50
    cemic
    -0.49
    ny
    -0.48
     Warsaw
    -0.48
    POSITIVE LOGITS
     testimonies
    0.66
    onyms
    0.66
     allegations
    0.65
     voluntarily
    0.64
     accusations
    0.59
     anonymously
    0.56
    imately
    0.55
     accus
    0.55
    ffer
    0.55
    dden
    0.55
    Activations Density 9.479%

    No Known Activations