© 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. 39437
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process

    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
    +0.14
    0.7%
    7
    +0.10
    0.5%
    483
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.26
    665
    +0.10
    0.15
    119
    +0.10
    0.11
    Negative Logits
    gru
    -0.67
    court
    -0.65
    foundland
    -0.64
     Frazier
    -0.62
    pict
    -0.58
    combe
    -0.58
    erion
    -0.55
    np
    -0.54
    uria
    -0.53
     Tanz
    -0.53
    POSITIVE LOGITS
    ?:
    0.71
    Ô
    0.69
    ?),
    0.68
     reconcile
    0.66
    ?]
    0.65
    vre
    0.65
     reconcil
    0.64
     handle
    0.63
     navigate
    0.62
     circumvent
    0.62
    Activations Density 12.884%

    No Known Activations