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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 34291
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and historical contexts

    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
    526
    +0.09
    0.6%
    566
    +0.08
    0.6%
    572
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.09
    0.30
    138
    +0.08
    0.28
    64
    +0.08
    -0.19
    Negative Logits
     Alph
    -0.54
    lished
    -0.50
    pring
    -0.49
    ILY
    -0.45
    iates
    -0.45
    ession
    -0.44
    ENDED
    -0.44
     Miche
    -0.43
    iating
    -0.43
    iants
    -0.43
    POSITIVE LOGITS
    ithe
    0.80
    atre
    0.75
    rette
    0.71
    phe
    0.63
    cium
    0.63
    ck
    0.62
    tery
    0.60
    reen
    0.59
    ¡
    0.58
    aviour
    0.58
    Activations Density 7.927%

    No Known Activations