© 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. 1134
    Prev
    Next
    INDEX
    Explanations

    phrases referring to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "someone" indicating interpersonal relationships or actions involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ird
    -0.67
    gradation
    -0.61
    ses
    -0.60
    wide
    -0.59
    ep
    -0.58
    ®
    -0.56
    aves
    -0.56
     Brief
    -0.55
    eties
    -0.55
    including
    -0.55
    POSITIVE LOGITS
     someone
    3.19
     somebody
    2.91
    someone
    2.87
     Someone
    2.29
    Someone
    2.17
     Somebody
    1.76
     anyone
    1.73
     whoever
    1.68
     anybody
    1.61
     something
    1.55
    Activations Density 0.022%

    No Known Activations