© 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. 22543
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    prominent figures and references to their actions or opinions

    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
    owship
    -0.75
    Also
    -0.72
    Secondly
    -0.70
     secondly
    -0.69
    ationally
    -0.68
    arching
    -0.68
    qqa
    -0.67
     Also
    -0.64
     furthermore
    -0.63
    actly
    -0.62
    POSITIVE LOGITS
     concede
    1.17
     concedes
    1.10
     admits
    1.05
     admit
    1.04
     acknowledges
    0.95
     acknowledge
    0.89
     conceded
    0.85
     couldn
    0.79
     whiff
    0.77
     admitting
    0.77
    Activations Density 0.182%

    No Known Activations