© 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. 33199
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions and personal experiences

    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
    320
    +0.07
    0.5%
    555
    +0.06
    0.4%
    107
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.07
    0.08
    375
    +0.06
    0.05
    107
    +0.06
    0.04
    Negative Logits
    netflix
    -0.44
     Cutting
    -0.41
    izabeth
    -0.40
    rawdownloadcloneembedreportprint
    -0.39
     mats
    -0.39
    icut
    -0.38
    urgy
    -0.38
    lighting
    -0.38
    ogun
    -0.37
    olded
    -0.37
    POSITIVE LOGITS
    hap
    0.54
    chev
    0.53
     someday
    0.53
    be
    0.49
     be
    0.48
    ivably
    0.48
    lege
    0.48
    hya
    0.48
    idate
    0.47
    rue
    0.46
    Activations Density 10.270%

    No Known Activations