© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13677
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events

    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
    679
    +0.18
    0.7%
    447
    +0.15
    0.6%
    739
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.18
    0.02
    679
    +0.15
    0.14
    640
    +0.14
    0.16
    Negative Logits
    izards
    -0.88
    pmwiki
    -0.87
    mini
    -0.86
    ASE
    -0.84
    ãĥīãĥ©ãĤ´ãĥ³
    -0.81
    cci
    -0.79
    BuyableInstoreAndOnline
    -0.78
     mart
    -0.77
    aine
    -0.74
     Brothers
    -0.74
    POSITIVE LOGITS
    manship
    0.98
    Ħ¢
    0.94
    olicy
    0.91
     ahead
    0.90
    eering
    0.89
    wards
    0.85
    boards
    0.80
     generations
    0.75
    dated
    0.75
    noon
    0.74
    Activations Density 7.848%

    No Known Activations