© 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. 35037
    Prev
    Next
    INDEX
    Explanations

    philosophical or inspirational quotes and passages

    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
    226
    +0.07
    0.5%
    152
    +0.06
    0.5%
    737
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.07
    0.12
    246
    +0.06
    0.12
    762
    +0.06
    0.16
    Negative Logits
    PF
    -0.50
    Sample
    -0.47
    USS
    -0.45
    IFF
    -0.43
    Vari
    -0.40
    ormal
    -0.39
    Lot
    -0.38
    Quant
    -0.38
    catentry
    -0.38
    ranged
    -0.38
    POSITIVE LOGITS
     democracy
    0.56
     democracies
    0.55
     Democracy
    0.54
     patri
    0.51
     prosperity
    0.50
    heid
    0.50
     democr
    0.49
     righteousness
    0.48
     destiny
    0.45
    ocracy
    0.45
    Activations Density 7.787%

    No Known Activations