© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    actions related to overwhelming or invading a space

    oai_token-act-pair · gpt-3.5-turbo

    terms related to large groups of people congregating or computer intrusions

    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
    ials
    -0.71
    rique
    -0.68
    loss
    -0.68
    weather
    -0.63
    rip
    -0.62
    cz
    -0.61
    anse
    -0.60
    onel
    -0.60
    ijk
    -0.59
    otics
    -0.59
    POSITIVE LOGITS
     into
    1.41
     onto
    1.17
     INTO
    1.17
     Into
    1.03
    into
    0.88
    kered
    0.82
     away
    0.72
    hered
    0.69
     up
    0.67
     Capitol
    0.66
    Activations Density 0.165%

    No Known Activations