Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13566
    Prev
    Next
    INDEX
    Explanations

    actions and solutions related to addressing social, economic, and technological issues

    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
    +0.39
    1.6%
    276
    +0.12
    0.5%
    229
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.39
    0.18
    405
    +0.12
    0.14
    276
    +0.12
    0.16
    Negative Logits
    ãĤ´ãĥ³
    -0.72
     Dresden
    -0.70
     hemor
    -0.67
    usterity
    -0.65
     towels
    -0.63
    ascript
    -0.62
     lawy
    -0.61
    bered
    -0.61
    signed
    -0.60
    wed
    -0.59
    POSITIVE LOGITS
    oca
    0.82
    uce
    0.70
    ealous
    0.70
    uate
    0.69
    INESS
    0.67
    FK
    0.65
    igmat
    0.64
     refres
    0.63
     maxim
    0.62
     RELEASE
    0.61
    Activations Density 13.605%

    No Known Activations