© 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. 4-RES-JB
    11. 14665
    Prev
    Next
    INDEX
    Explanations

    phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks in the text

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

    No Comments

    Negative Logits
    OME
    -0.86
    rencies
    -0.82
     CLIENT
    -0.76
    ply
    -0.76
    payer
    -0.74
    MpServer
    -0.74
    soever
    -0.73
    urat
    -0.73
     Flavoring
    -0.71
     DEBUG
    -0.68
    POSITIVE LOGITS
     Bris
    0.75
     Shack
    0.74
     Falk
    0.74
    belt
    0.65
     Wis
    0.63
     Chic
    0.62
     Sieg
    0.62
     Ig
    0.62
    rave
    0.61
     SOS
    0.61
    Activations Density 0.000%

    No Known Activations