© 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. 7-RES-JB
    11. 17113
    Prev
    Next
    INDEX
    Explanations

    mentions of successful and impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently in complex sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    payer
    -0.74
    ocument
    -0.74
    Enlarge
    -0.74
    iste
    -0.73
    itarian
    -0.69
    ieg
    -0.69
    DX
    -0.69
    uct
    -0.68
     FOIA
    -0.68
     Written
    -0.67
    POSITIVE LOGITS
     teammate
    0.93
     hopefully
    0.88
     then
    0.84
     thus
    0.84
     teammates
    0.83
     Sporting
    0.82
     athleticism
    0.81
     rookies
    0.79
     rookie
    0.78
     sporting
    0.77
    Activations Density 0.247%

    No Known Activations