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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45487
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to server settings and configurations

    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
    +0.30
    1.3%
    682
    +0.13
    0.5%
    59
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    649
    +0.30
    0.03
    442
    +0.13
    0.06
    741
    +0.12
    0.05
    Negative Logits
    hya
    -0.90
    itious
    -0.86
    ition
    -0.83
    umar
    -0.80
    ĸļ
    -0.80
    itives
    -0.79
    ible
    -0.78
    itsch
    -0.78
    orne
    -0.76
    orical
    -0.76
    POSITIVE LOGITS
     overloaded
    0.85
     admins
    0.82
     operated
    0.80
     reception
    0.80
     operating
    0.78
    izen
    0.75
     farms
    0.75
     sshd
    0.73
     server
    0.72
    Deploy
    0.71
    Activations Density 5.886%

    No Known Activations