© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18602
    Prev
    Next
    INDEX
    Explanations

    aspects of things or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various components or features of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amaz
    -0.75
    anders
    -0.75
    ander
    -0.73
    gently
    -0.70
    odore
    -0.68
    prus
    -0.67
    ESCO
    -0.64
    claimed
    -0.63
    tails
    -0.63
    helm
    -0.63
    POSITIVE LOGITS
     thereof
    1.21
     of
    1.09
    ality
    0.88
    Of
    0.85
    ial
    0.85
    ials
    0.80
     aspects
    0.78
    hetical
    0.78
     Of
    0.77
    ially
    0.76
    Activations Density 0.055%

    No Known Activations