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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 33276
    Prev
    Next
    INDEX
    Explanations

    plans or intentions for future actions or developments

    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
    +0.16
    0.8%
    649
    +0.13
    0.6%
    575
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.16
    0.18
    288
    +0.13
    0.23
    274
    +0.12
    0.10
    Negative Logits
    mint
    -0.76
     ILCS
    -0.72
    iencies
    -0.70
     Temper
    -0.69
    BuyableInstoreAndOnline
    -0.68
    Cause
    -0.68
    avis
    -0.66
    Interstitial
    -0.66
    ochet
    -0.63
    inas
    -0.62
    POSITIVE LOGITS
    etary
    0.75
     hatched
    0.73
     obs
    0.73
    ller
    0.69
     timetable
    0.68
     ahead
    0.67
    escape
    0.66
     plans
    0.65
     ambitious
    0.65
    htar
    0.64
    Activations Density 10.323%

    No Known Activations