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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35089
    Prev
    Next
    INDEX
    Explanations

    phrases relating to time, continuity, and progression

    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
    71
    +0.12
    0.6%
    184
    +0.10
    0.5%
    279
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.12
    0.10
    184
    +0.10
    0.05
    8
    +0.10
    0.09
    Negative Logits
    agra
    -0.69
    ahime
    -0.68
    haps
    -0.67
    ells
    -0.62
    omas
    -0.61
    dinand
    -0.61
    =-=-=-=-=-=-=-=-
    -0.61
    ello
    -0.60
    onym
    -0.59
    odore
    -0.57
    POSITIVE LOGITS
     except
    0.74
     conclud
    0.68
     thereafter
    0.66
     Kessler
    0.63
    ÏĤ
    0.62
    around
    0.61
     revolves
    0.60
     imaginable
    0.58
     alike
    0.58
    cape
    0.57
    Activations Density 5.000%

    No Known Activations