© 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. 22584
    Prev
    Next
    INDEX
    Explanations

    mentions of customization options for various products

    oai_token-act-pair · gpt-3.5-turbo

    references to customization or personalized options

    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
    trump
    -0.81
    ï¸
    -0.79
    loo
    -0.72
     Lauder
    -0.69
    enance
    -0.69
    wick
    -0.69
     CrossRef
    -0.68
     Kinn
    -0.68
    ·
    -0.67
    Æ
    -0.67
    POSITIVE LOGITS
    isable
    1.69
    izations
    1.61
    izable
    1.44
    ised
    1.38
    isations
    1.37
    isation
    1.27
    arily
    1.26
    ization
    1.14
    izing
    1.07
    ized
    1.07
    Activations Density 0.038%

    No Known Activations