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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 3599
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    entities and specific locations or organizations involved in research and funding activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     antioxid
    -0.81
    Balt
    -0.81
    GoldMagikarp
    -0.80
    natureconservancy
    -0.75
     largeDownload
    -0.71
     behavi
    -0.70
    DAQ
    -0.69
    PDATE
    -0.68
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.68
    HUD
    -0.67
    POSITIVE LOGITS
    ividual
    0.91
    ogun
    0.72
    irlf
    0.71
    othal
    0.70
    ruary
    0.66
    onga
    0.66
    itially
    0.66
    ruciating
    0.64
    ecause
    0.63
    bidden
    0.63
    Activations Density 15.794%

    No Known Activations