© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1070
    Prev
    Next
    INDEX
    Explanations

    mentions of missing items or errors that need to be corrected

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or amounts in various contexts

    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
    )."
    -1.01
    .")
    -0.73
    .'"
    -0.72
    '."
    -0.70
    ]."
    -0.69
    .""
    -0.67
    "></
    -0.60
    "/>
    -0.59
    !'"
    -0.59
    )</
    -0.56
    POSITIVE LOGITS
     respectively
    0.46
    DCS
    0.44
    aido
    0.43
    oat
    0.41
     Legion
    0.40
     crossover
    0.40
    itled
    0.40
     CTR
    0.39
     GOT
    0.38
    rolet
    0.37
    Activations Density 2.395%

    No Known Activations