© 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. 11-RES-JB
    11. 4197
    Prev
    Next
    INDEX
    Explanations

    references to openness or things being open

    oai_token-act-pair · gpt-3.5-turbo

    terms related to openness and transparency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otos
    -0.74
    rior
    -0.72
    dos
    -0.70
    CTV
    -0.63
     Statue
    -0.62
    iage
    -0.61
    vous
    -0.61
     Kamp
    -0.61
     Sequ
    -0.61
    doms
    -0.60
    POSITIVE LOGITS
     minded
    0.96
    ended
    0.84
     ended
    0.84
     source
    0.83
     invitation
    0.82
    hearted
    0.82
     door
    0.81
     enrollment
    0.80
     borders
    0.80
     sourced
    0.79
    Activations Density 0.046%

    No Known Activations