© 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. 6-RES-JB
    11. 14407
    Prev
    Next
    INDEX
    Explanations

    expressions related to academic discussions or research findings

    oai_token-act-pair · gpt-3.5-turbo

    words related to evaluations or identifiers of students or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įå¥ij士
    -0.74
     Negro
    -0.65
     Marble
    -0.64
     prol
    -0.63
     Shutterstock
    -0.63
     visitor
    -0.63
     snail
    -0.62
     Whit
    -0.61
     Golem
    -0.61
     Sakuya
    -0.61
    POSITIVE LOGITS
    selves
    0.97
    hip
    0.89
    acca
    0.86
    particularly
    0.83
    agree
    0.82
    were
    0.79
    ¹
    0.79
    assembled
    0.78
    chool
    0.78
    including
    0.78
    Activations Density 0.238%

    No Known Activations