© 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. 8-RES-JB
    11. 8646
    Prev
    Next
    INDEX
    Explanations

    statements indicating a reason or cause

    oai_token-act-pair · gpt-3.5-turbo

    phrases that articulate explanations or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KY
    -0.72
    agog
    -0.69
     Carbuncle
    -0.68
    chance
    -0.61
     Gleaming
    -0.59
    kil
    -0.59
    ipel
    -0.59
    lasses
    -0.59
    asts
    -0.58
    semble
    -0.58
    POSITIVE LOGITS
     why
    1.31
    abl
    1.22
    why
    0.99
     WHY
    0.95
     behind
    0.93
     cited
    0.83
     rationale
    0.75
     Why
    0.73
    ably
    0.73
     justifying
    0.71
    Activations Density 0.032%

    No Known Activations