© 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. 18822
    Prev
    Next
    INDEX
    Explanations

    references to the term "Che" which seems to be associated with various contexts such as people, places, or cultural references

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person or character, likely associated with a notable public figure or cultural icon

    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
    nings
    -0.75
    imately
    -0.73
    hower
    -0.71
    ception
    -0.70
    ugal
    -0.69
    CEPT
    -0.68
    ceived
    -0.66
    structed
    -0.64
    Ire
    -0.64
    ZI
    -0.63
    POSITIVE LOGITS
    chens
    0.91
    enhagen
    0.90
    bies
    0.88
    bler
    0.88
    shaw
    0.84
    bie
    0.83
    irrel
    0.83
    resy
    0.83
    loo
    0.83
    cery
    0.80
    Activations Density 0.060%

    No Known Activations