© 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. 33977
    Prev
    Next
    INDEX
    Explanations

    real-world scenarios or stories describing interactions and experiences at stalls, especially related to businesses or community spaces

    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
    288
    +0.18
    0.8%
    68
    +0.11
    0.5%
    360
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.23
    288
    +0.11
    0.25
    659
    +0.10
    0.09
    Negative Logits
    vernment
    -0.77
    éĹĺ
    -0.75
    gments
    -0.74
    vironment
    -0.73
    ointed
    -0.67
     GOODMAN
    -0.66
     largeDownload
    -0.64
    âĵĺ
    -0.64
    ortium
    -0.63
    itars
    -0.63
    POSITIVE LOGITS
    ioned
    1.06
    ions
    0.98
    wagon
    0.93
    ion
    0.93
     stall
    0.93
     stalls
    0.87
    holders
    0.86
    ional
    0.82
    ua
    0.80
    iao
    0.79
    Activations Density 8.019%

    No Known Activations