Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18333
    Prev
    Next
    INDEX
    Explanations

    questions, problems, and goals related to a topic

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with challenges or issues being addressed in discussions

    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
     Doors
    -0.65
     Speedway
    -0.59
     Sins
    -0.59
    pen
    -0.59
     Font
    -0.59
     liquids
    -0.58
     Tro
    -0.58
     Regist
    -0.56
     Room
    -0.56
     Surprise
    -0.55
    POSITIVE LOGITS
    isphere
    0.89
    cture
    0.76
    iatus
    0.75
    illet
    0.74
    igue
    0.73
    eta
    0.69
    ungle
    0.67
    ylon
    0.67
    ichick
    0.66
    folio
    0.64
    Activations Density 0.327%

    No Known Activations