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. 3664
    Prev
    Next
    INDEX
    Explanations

    code snippets or references related to a specific programming language or technology

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "GL" 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
    cling
    -0.71
    Rated
    -0.68
    oxide
    -0.63
    taining
    -0.63
    ãĥĩ
    -0.63
    joined
    -0.63
    raviolet
    -0.62
    ItemTracker
    -0.62
    cle
    -0.62
    selage
    -0.62
    POSITIVE LOGITS
    ength
    1.07
    ENN
    0.99
    ASS
    0.90
    ibrary
    0.88
    FW
    0.88
    OCK
    0.87
    ocaust
    0.85
    ibr
    0.83
    oad
    0.82
    INTON
    0.82
    Activations Density 0.009%

    No Known Activations