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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 23192
    Prev
    Next
    INDEX
    Explanations

    disclaimers or statements indicating opinions expressed are the author's own

    oai_token-act-pair · gpt-3.5-turbo

    statements about the author's opinions and their distinction from others' views

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trap
    -0.60
     Inspection
    -0.59
    delay
    -0.59
    locks
    -0.56
     brut
    -0.55
     sped
    -0.55
     shuffle
    -0.54
     tha
    -0.54
    İĭ
    -0.54
     charms
    -0.54
    POSITIVE LOGITS
     opinions
    0.90
    column
    0.74
     editorial
    0.73
    ãĤ¤ãĥĪ
    0.70
     authors
    0.69
     viewpoints
    0.68
     Contribut
    0.67
     contributors
    0.66
     expressed
    0.66
     Inquis
    0.66
    Activations Density 0.084%

    No Known Activations