© 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
    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. 19406
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that do not correspond to any meaningful linguistic pattern and likely represent noise in the data

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical or coded sequences that may indicate technical details or measurements

    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
    natureconservancy
    -0.51
    untarily
    -0.51
    achev
    -0.49
    reau
    -0.49
    ierrez
    -0.48
    erto
    -0.48
    à©
    -0.48
    taboola
    -0.48
    imeters
    -0.47
    bard
    -0.47
    POSITIVE LOGITS
    custom
    0.52
     Saud
    0.50
     gran
    0.47
    uci
    0.45
     Witnesses
    0.45
    she
    0.45
     Lilith
    0.45
     Yug
    0.45
    apest
    0.44
    llah
    0.44
    Activations Density 1.786%

    No Known Activations