© 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. 17141
    Prev
    Next
    INDEX
    Explanations

    locations or entities mentioned in a news or crime report

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the"

    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
    omics
    -0.79
    heit
    -0.72
     ç¥ŀ
    -0.72
    æĹ
    -0.71
    etically
    -0.71
    ipedia
    -0.70
    igue
    -0.69
    RGB
    -0.69
    ingly
    -0.69
    notes
    -0.69
    POSITIVE LOGITS
     incident
    1.16
     latter
    1.14
     offending
    1.05
     remainder
    1.03
     altercation
    1.02
     alleged
    1.01
     same
    0.99
     arresting
    0.99
     ensuing
    0.97
     aforementioned
    0.97
    Activations Density 0.617%

    No Known Activations