© 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. 9-RES-JB
    11. 13237
    Prev
    Next
    INDEX
    Explanations

    technical information such as specific capacities or data points

    oai_token-act-pair · gpt-3.5-turbo

    event-related information and details about performance or timing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.71
    ccording
    -0.68
    ãĥķãĤ©
    -0.67
    IDA
    -0.65
    indal
    -0.63
    conservancy
    -0.63
     Unle
    -0.63
    Tweet
    -0.62
    acl
    -0.61
    =-=-=-=-=-=-=-=-
    -0.59
    POSITIVE LOGITS
     again
    0.77
     TBD
    0.76
     either
    0.75
     unspecified
    0.74
     TBA
    0.71
     unchanged
    0.71
     laps
    0.70
     same
    0.69
     opposite
    0.65
     both
    0.64
    Activations Density 0.374%

    No Known Activations