© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 11893
    Prev
    Next
    INDEX
    Explanations

    words related to separation or division

    oai_token-act-pair · gpt-3.5-turbo

    mentions of paralysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.92
    OME
    -0.78
    士
    -0.76
    éĹĺ
    -0.73
    ¥µ
    -0.73
    ELD
    -0.72
     Carbuncle
    -0.71
    hower
    -0.71
    hirt
    -0.69
    andestine
    -0.67
    POSITIVE LOGITS
    allel
    1.03
    ietal
    0.95
    rot
    0.94
    amount
    0.93
    abolic
    0.91
    anoia
    0.90
    ison
    0.89
    rots
    0.88
    icularly
    0.86
    agraph
    0.86
    Activations Density 0.015%

    No Known Activations