© 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. 4007
    Prev
    Next
    INDEX
    Explanations

    positive and negative evaluations or critiques

    oai_token-act-pair · gpt-3.5-turbo

    sections that provide critiques or evaluations

    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
    oud
    -0.84
    itol
    -0.79
    izons
    -0.75
    onet
    -0.73
    agon
    -0.70
    ozo
    -0.70
    inement
    -0.69
     equivalents
    -0.69
    urat
    -0.69
    izo
    -0.69
    POSITIVE LOGITS
     Provided
    0.79
     TBD
    0.77
     Bye
    0.76
     Scores
    0.76
     Nope
    0.73
     Column
    0.73
     Named
    0.73
     Photograph
    0.72
     Anyone
    0.71
     Yeah
    0.71
    Activations Density 0.136%

    No Known Activations