© 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
    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. 5993
    Prev
    Next
    INDEX
    Explanations

    mentions of current events and news articles

    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
    640
    +0.28
    0.9%
    453
    +0.17
    0.6%
    330
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.10
    561
    +0.17
    0.07
    160
    +0.14
    0.07
    Negative Logits
    ieve
    -0.91
    ichick
    -0.88
    aration
    -0.82
     Exhibition
    -0.82
     congr
    -0.82
     ital
    -0.82
     express
    -0.81
     Bender
    -0.79
     deductions
    -0.79
    cv
    -0.79
    POSITIVE LOGITS
    CLE
    1.20
    CLUS
    1.18
    SAN
    1.13
    BAT
    1.12
    ccording
    1.11
    LIST
    1.10
    VID
    1.10
    SHARE
    1.08
    UG
    1.07
    HOU
    1.03
    Activations Density 0.515%

    No Known Activations