© 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. 1934
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "Mak" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    words starting with "Mak"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    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
    343
    +0.13
    0.6%
    618
    +0.10
    0.5%
    374
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.11
    288
    +0.10
    0.13
    343
    +0.10
    0.09
    Negative Logits
    âĸ¬
    -0.75
    FACE
    -0.73
    ected
    -0.73
    phrine
    -0.73
    rics
    -0.72
    IFIC
    -0.72
     Reaper
    -0.72
    perse
    -0.70
    Interstitial
    -0.69
    cised
    -0.69
    POSITIVE LOGITS
    olulu
    0.98
    arov
    0.89
    imura
    0.88
    azel
    0.87
    irit
    0.87
    onew
    0.84
    htar
    0.83
    waukee
    0.80
    itude
    0.78
    ills
    0.77
    Activations Density 1.646%

    No Known Activations