© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14383
    Prev
    Next
    INDEX
    Explanations

    dates or years mentioned in textual content

    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
    393
    +0.31
    1.3%
    59
    +0.12
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.31
    0.09
    380
    +0.12
    0.08
    546
    +0.11
    0.09
    Negative Logits
    ãĤ´ãĥ³
    -0.81
    arah
    -0.79
    arily
    -0.73
    obook
    -0.72
    ullivan
    -0.68
    rack
    -0.68
    orb
    -0.68
    arse
    -0.68
    Display
    -0.67
    avior
    -0.67
    POSITIVE LOGITS
     however
    1.32
     meanwhile
    1.09
     moreover
    1.01
     although
    0.93
     though
    0.92
     when
    0.84
     according
    0.82
     respectively
    0.81
    lished
    0.79
    when
    0.75
    Activations Density 1.320%

    No Known Activations