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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 814
    Prev
    Next
    INDEX
    Explanations

    time-related terms and references, such as dates, months, years, and time intervals

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    161
    +0.14
    0.5%
    248
    +0.14
    0.5%
    720
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.01
    706
    +0.14
    0.03
    600
    +0.13
    0.03
    Negative Logits
    tein
    -1.01
    schild
    -0.97
    uador
    -0.85
    ELF
    -0.81
    negie
    -0.80
    raq
    -0.80
    mble
    -0.79
    olves
    -0.79
    iday
    -0.78
    FACE
    -0.78
    POSITIVE LOGITS
     Edited
    1.16
     Tracker
    0.86
     Breed
    0.84
    acan
    0.81
    Brend
    0.78
    ont
    0.77
     âĨij
    0.74
    anche
    0.73
     Riders
    0.72
     Birds
    0.72
    Activations Density 0.121%

    No Known Activations