© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    track the progress or trajectory towards a goal or outcome

    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
    316
    +0.07
    0.5%
    575
    +0.07
    0.5%
    207
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.07
    0.06
    490
    +0.07
    0.06
    446
    +0.07
    0.07
    Negative Logits
    ilies
    -0.44
    cu
    -0.44
    outine
    -0.44
     Lives
    -0.43
    interest
    -0.43
     Milton
    -0.43
    rent
    -0.42
    ppings
    -0.42
    hee
    -0.42
    ole
    -0.41
    POSITIVE LOGITS
    Ĥİ
    0.48
    à¥
    0.47
     induction
    0.46
    âĢ¢âĢ¢
    0.43
    Result
    0.42
     conver
    0.42
    ãĥī
    0.42
    00007
    0.42
    ãĥ¼ãĥĨ
    0.41
     guiActiveUn
    0.41
    Activations Density 6.737%

    No Known Activations