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

    Neuronpedia

    Jacobian LensNEW
    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. 1066
    Prev
    Next
    INDEX
    Explanations

    last-minute changes or events in various contexts such as events, decisions, or announcements

    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
    706
    +0.16
    0.5%
    381
    +0.14
    0.4%
    462
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.16
    0.06
    262
    +0.14
    0.04
    115
    +0.14
    0.06
    Negative Logits
    ename
    -1.24
    usky
    -1.20
    ENCE
    -1.20
    young
    -1.19
    atin
    -1.14
    ector
    -1.13
    heon
    -1.12
    ivil
    -1.10
    udeb
    -1.09
     Halls
    -1.08
    POSITIVE LOGITS
    aneously
    1.40
     dispatch
    1.25
     burst
    1.21
     turnaround
    1.14
     maneuver
    1.11
     glance
    1.11
     preparations
    1.09
     blockers
    1.06
     skirm
    1.06
     gratification
    1.06
    Activations Density 1.608%

    No Known Activations