© 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. 1391
    Prev
    Next
    INDEX
    Explanations

    references to sources or authorities

    oai_token-act-pair · gpt-3.5-turbo

    references to historical views and theories presented by specific individuals

    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
    oided
    -0.74
    boxing
    -0.74
    hene
    -0.73
    verage
    -0.73
    itaire
    -0.72
    uality
    -0.71
    cliffe
    -0.69
    itto
    -0.67
    forge
    -0.67
    igger
    -0.66
    POSITIVE LOGITS
     economists
    1.14
     proponents
    1.12
     Professor
    1.09
     Aristotle
    1.08
     economist
    1.07
     philosophers
    1.05
     commentators
    1.04
     psychologists
    1.03
     theorists
    1.03
     philosopher
    1.01
    Activations Density 0.296%

    No Known Activations