© 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. 39422
    Prev
    Next
    INDEX
    Explanations

    information related to cooperatives and cooperative activities

    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
    +0.13
    0.5%
    567
    +0.12
    0.5%
    763
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.13
    0.08
    517
    +0.12
    0.08
    368
    +0.11
    0.10
    Negative Logits
    ItemThumbnailImage
    -0.75
    Quantity
    -0.74
    ¥µ
    -0.70
     Pog
    -0.67
    Recomm
    -0.67
     Frie
    -0.66
     seiz
    -0.65
     millisec
    -0.65
    Skill
    -0.64
     Feast
    -0.63
    POSITIVE LOGITS
    rency
    1.27
    reau
    0.90
    lear
    0.85
    heartedly
    0.81
    ocated
    0.78
    nect
    0.78
    hers
    0.77
    atorial
    0.77
    mun
    0.77
    cil
    0.77
    Activations Density 12.022%

    No Known Activations