© 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. 10-RES-JB
    11. 11136
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    specifications and technical details of electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orc
    -0.75
     volunt
    -0.71
    terson
    -0.67
     Fallen
    -0.66
     Royals
    -0.65
     theirs
    -0.64
    roth
    -0.62
    arro
    -0.62
     Frey
    -0.61
     Garrison
    -0.61
    POSITIVE LOGITS
    GB
    1.20
    TB
    1.13
    MP
    1.08
    Gb
    1.05
    Mbps
    0.98
    MB
    0.95
    GHz
    0.92
    LB
    0.91
    200
    0.88
    dB
    0.88
    Activations Density 0.078%

    No Known Activations