© 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. 11-RES-JB
    6. 9391
    Prev
    Next
    INDEX
    Explanations

    quotations and specific phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks or instances of direct speech in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accomp
    -0.95
     liner
    -0.81
     volley
    -0.79
     brim
    -0.77
     carrier
    -0.77
     fault
    -0.76
     flourish
    -0.76
     flared
    -0.75
     rul
    -0.74
     bracket
    -0.73
    POSITIVE LOGITS
    We
    1.52
    Nobody
    1.52
    there
    1.52
    Everybody
    1.51
    Every
    1.50
    There
    1.50
    If
    1.49
    Everything
    1.49
    Nothing
    1.49
    Everyone
    1.49
    Activations Density 0.127%

    No Known Activations