© 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. 1-RES-JB
    11. 3201
    Prev
    Next
    INDEX
    Explanations

    references to paperback books and ISBN numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to book formats and publishing details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adra
    -0.84
    nel
    -0.83
    aviour
    -0.73
    amera
    -0.73
    pes
    -0.73
    ide
    -0.72
    antics
    -0.70
    inance
    -0.70
    udes
    -0.69
    rera
    -0.69
    POSITIVE LOGITS
     ISBN
    1.25
     bookstore
    1.21
    lishing
    1.00
     Publishers
    0.99
    lisher
    0.96
    éĸ
    0.96
    stores
    0.93
     Books
    0.92
    Books
    0.91
     paperback
    0.89
    Activations Density 0.033%

    No Known Activations