© 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. 6497
    Prev
    Next
    INDEX
    Explanations

    phrases related to data-related activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data collection and management

    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
    urnal
    -0.82
    zl
    -0.79
    ãĥĥãĥī
    -0.77
    SN
    -0.72
    otta
    -0.71
    ulet
    -0.70
    {"
    -0.67
    ofi
    -0.66
    mount
    -0.65
    hift
    -0.64
    POSITIVE LOGITS
     techniques
    0.97
     tools
    0.88
     prevention
    0.88
     machinery
    0.87
     process
    0.87
     tool
    0.87
     chores
    0.86
     efforts
    0.86
     procedures
    0.86
     strategies
    0.86
    Activations Density 0.234%

    No Known Activations