© 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. 22461
    Prev
    Next
    INDEX
    Explanations

    statistical or numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and associated metrics

    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
    izoph
    -0.72
    furt
    -0.63
    eteria
    -0.63
    abal
    -0.61
     consecut
    -0.59
     intent
    -0.59
     bitten
    -0.59
    icians
    -0.59
    pecially
    -0.58
    geries
    -0.58
    POSITIVE LOGITS
     ±
    0.77
    isSpecialOrderable
    0.76
     crore
    0.74
    billion
    0.74
    ĸļ
    0.70
    rc
    0.68
     Converted
    0.65
    ahime
    0.64
     Percent
    0.63
     Convert
    0.63
    Activations Density 0.217%

    No Known Activations