© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    time-related phrases

    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
    271
    +0.10
    0.5%
    726
    +0.09
    0.5%
    283
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.17
    640
    +0.09
    0.22
    442
    +0.09
    0.10
    Negative Logits
    abal
    -0.71
    adia
    -0.69
    ading
    -0.69
    ounding
    -0.68
    ettel
    -0.67
    asive
    -0.65
    andi
    -0.64
    opoulos
    -0.63
    iants
    -0.63
    Reviewer
    -0.63
    POSITIVE LOGITS
    theless
    0.75
     ago
    0.70
    hower
    0.69
     Ago
    0.67
     ILCS
    0.67
    soDeliveryDate
    0.62
    frames
    0.61
    fw
    0.60
     2021
    0.60
    DAY
    0.59
    Activations Density 7.238%

    No Known Activations