© 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. 8-RES-JB
    11. 8980
    Prev
    Next
    INDEX
    Explanations

    proper nouns, likely related to appearances or mentions in various media platforms

    oai_token-act-pair · gpt-3.5-turbo

    instances of appearances or mentions in the media or public events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     served
    -0.70
    .–
    -0.70
     mishand
    -0.67
     handled
    -0.67
    hesda
    -0.65
     maintained
    -0.64
    ··
    -0.64
    gencies
    -0.63
    âĢķ
    -0.63
     prefers
    -0.62
    POSITIVE LOGITS
    Picture
    0.80
    ONY
    0.70
    ¥µ
    0.69
     Occupations
    0.68
     silhouette
    0.67
     commercials
    0.67
    agon
    0.67
     Playboy
    0.66
     advertisements
    0.66
    action
    0.65
    Activations Density 0.186%

    No Known Activations