© 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. 0-RES-JB
    11. 16408
    Prev
    Next
    INDEX
    Explanations

    names or words that contain the substring "vict"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cube
    -0.75
     hazard
    -0.72
     Reed
    -0.70
     draft
    -0.70
     Herz
    -0.69
     Schmidt
    -0.69
     PARK
    -0.68
     appendix
    -0.67
     shortage
    -0.67
     Ellison
    -0.67
    POSITIVE LOGITS
    vict
    3.16
    Vict
    2.11
    Mil
    1.56
    nered
    1.40
    assault
    1.17
    secut
    1.15
    weapons
    1.14
    DEM
    1.12
    Operation
    1.12
    birth
    1.10
    Activations Density 0.049%

    No Known Activations