© 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. 13761
    Prev
    Next
    INDEX
    Explanations

    occasions or instances of events or actions

    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
    +0.23
    1.2%
    151
    +0.09
    0.5%
    587
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.23
    0.09
    43
    +0.09
    0.07
    492
    +0.08
    0.07
    Negative Logits
    utenberg
    -0.63
    hemat
    -0.63
    agra
    -0.59
    track
    -0.59
    haul
    -0.57
    cott
    -0.57
    ogun
    -0.55
    hab
    -0.55
    hesive
    -0.55
    gebra
    -0.54
    POSITIVE LOGITS
     occasions
    0.95
    theless
    0.83
     occasion
    0.78
    EMBER
    0.65
    forth
    0.64
    orial
    0.64
    notes
    0.62
    enance
    0.62
    eve
    0.62
     instances
    0.60
    Activations Density 9.591%

    No Known Activations