© 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. 4968
    Prev
    Next
    INDEX
    Explanations

    names of characters in a written work and their interactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character Weiss and her interactions with others

    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
    Indiana
    -0.72
    vised
    -0.71
    ally
    -0.70
    Lay
    -0.69
    roit
    -0.68
    iotic
    -0.66
    consumer
    -0.66
    ITY
    -0.65
    ITIES
    -0.64
    SPONSORED
    -0.63
    POSITIVE LOGITS
     Schwarz
    1.00
    lda
    0.94
     Swift
    0.83
     Pyrrha
    0.80
     semblance
    0.75
     Yang
    0.75
    BY
    0.74
    ullivan
    0.74
    gang
    0.73
     Nik
    0.70
    Activations Density 0.042%

    No Known Activations