© 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. 22583
    Prev
    Next
    INDEX
    Explanations

    technical terms related to business, technology, and economics

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with metrics or measures of economic and operational performance

    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
    Pic
    -0.68
    Lear
    -0.68
    alle
    -0.67
    itional
    -0.66
    ieth
    -0.61
    tiny
    -0.61
    stown
    -0.60
    Gaming
    -0.60
    Clar
    -0.60
    asha
    -0.59
    POSITIVE LOGITS
     coupled
    0.85
     (>
    0.85
     (<
    0.74
     amidst
    0.71
     afforded
    0.69
    enance
    0.68
     prevail
    0.68
     due
    0.67
    cence
    0.66
     Draper
    0.66
    Activations Density 0.585%

    No Known Activations