© 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. 3-RES-JB
    11. 10764
    Prev
    Next
    INDEX
    Explanations

    declarative sentences involving the act of stating something

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or authoritative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rax
    -0.81
    ayson
    -0.75
    emis
    -0.73
    anos
    -0.72
    poons
    -0.71
    iffe
    -0.70
    atz
    -0.69
    atche
    -0.68
    thora
    -0.67
    ilan
    -0.64
    POSITIVE LOGITS
    SPONSORED
    0.91
    rooms
    0.86
     legislatures
    0.82
    mberg
    0.81
     governments
    0.74
    lessness
    0.69
    less
    0.68
     Governments
    0.66
     coercion
    0.66
    room
    0.66
    Activations Density 0.054%

    No Known Activations