© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    quotations or dialogue within text

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue within the text

    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
     scheduled
    -0.82
     lookout
    -0.78
     termin
    -0.76
     whistle
    -0.72
     displeasure
    -0.72
     punct
    -0.71
     roundup
    -0.71
     arch
    -0.71
     sleeper
    -0.70
     relaxing
    -0.70
    POSITIVE LOGITS
    They
    1.36
    We
    1.34
    It
    1.31
    Sometimes
    1.29
    Because
    1.29
    Nobody
    1.29
    There
    1.29
    Our
    1.29
    Anything
    1.26
    Unless
    1.23
    Activations Density 0.090%

    No Known Activations