© 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. 13438
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name or location, particularly "Irvine"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Irvin."

    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
     guiActiveUnfocused
    -0.75
     Butterfly
    -0.74
    ĸļ
    -0.73
    eries
    -0.71
    ãģ®éŃĶ
    -0.67
     CLSID
    -0.67
    姫
    -0.67
     Unch
    -0.66
    insula
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
    respective
    1.04
    relevant
    1.03
    cles
    0.89
    rational
    0.89
    regular
    0.89
    resist
    0.87
    idium
    0.87
    acial
    0.85
    rha
    0.84
    rig
    0.82
    Activations Density 0.017%

    No Known Activations