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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 33669
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict and political events, particularly including terms related to embargoes, protests, uprisings, and geopolitical negotiations

    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
    718
    +0.08
    0.5%
    526
    +0.08
    0.5%
    549
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.08
    0.20
    326
    +0.08
    0.18
    526
    +0.08
    -0.04
    Negative Logits
    wagen
    -0.59
    tone
    -0.58
    beard
    -0.57
    LED
    -0.56
    hyde
    -0.56
    dash
    -0.54
    nan
    -0.52
    shine
    -0.52
    omial
    -0.51
    loo
    -0.51
    POSITIVE LOGITS
     hur
    0.59
    itudinal
    0.54
    rying
    0.49
     unp
    0.49
    inen
    0.48
    ractor
    0.48
    ried
    0.48
    izoph
    0.48
    ================================================================
    0.47
    vor
    0.47
    Activations Density 5.552%

    No Known Activations