© 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. 4-RES-JB
    11. 10171
    Prev
    Next
    INDEX
    Explanations

    phrases related to deep contemplation or introspection

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "think about"

    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
    catentry
    -0.71
    Written
    -0.69
    roy
    -0.68
    edition
    -0.66
    IER
    -0.66
    ा
    -0.65
    waters
    -0.64
    ante
    -0.63
    SUP
    -0.63
    htm
    -0.63
    POSITIVE LOGITS
     how
    0.86
    pheus
    0.74
    agall
    0.74
     internally
    0.72
    agine
    0.72
     hypot
    0.72
     buying
    0.71
     reforming
    0.70
    thood
    0.69
     halfway
    0.69
    Activations Density 0.042%

    No Known Activations