© 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. 5065
    Prev
    Next
    INDEX
    Explanations

    references to the name "Cav" with varying numerical values after it

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cav" associated with various contexts

    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
    utenant
    -0.83
    zee
    -0.82
    ãĥ£
    -0.80
    ufact
    -0.74
     pleas
    -0.71
    selves
    -0.68
    ĪĴ
    -0.68
    stice
    -0.67
    mer
    -0.67
    slave
    -0.66
    POSITIVE LOGITS
    endish
    0.85
    iant
    0.82
    ity
    0.82
    aukee
    0.75
    iants
    0.74
    iar
    0.73
    ildo
    0.71
    iage
    0.70
    itate
    0.69
    illon
    0.69
    Activations Density 0.089%

    No Known Activations