© 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. 20341
    Prev
    Next
    INDEX
    Explanations

    special characters like hyphens

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "X-Men" and its related associations in 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
     EntityItem
    -0.71
     digestion
    -0.67
    ufact
    -0.67
     Cla
    -0.65
     Lauder
    -0.64
     msec
    -0.64
     diarr
    -0.63
     TODAY
    -0.63
     ABE
    -0.62
    ÙIJ
    -0.62
    POSITIVE LOGITS
    rays
    1.06
    cellent
    1.00
    shaped
    0.99
    Factor
    0.98
    ray
    0.95
    axis
    0.95
    Men
    0.93
    factor
    0.93
    reme
    0.91
    Ray
    0.88
    Activations Density 0.027%

    No Known Activations