© 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. 747
    Prev
    Next
    INDEX
    Explanations

    keywords related to software testing and debugging

    oai_token-act-pair · gpt-3.5-turbo

    terms related to testing and debugging processes

    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
    NetMessage
    -0.75
    soType
    -0.74
    taboola
    -0.72
    entric
    -0.70
    ACP
    -0.70
    wcs
    -0.68
    ols
    -0.67
    riminal
    -0.66
    yles
    -0.66
    afort
    -0.65
    POSITIVE LOGITS
     suite
    1.06
    udo
    1.02
     suites
    1.00
    bench
    0.96
    imony
    0.87
     dummy
    0.82
     sandbox
    0.80
    server
    0.79
     session
    0.77
     sessions
    0.75
    Activations Density 0.104%

    No Known Activations