© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7435
    Prev
    Next
    INDEX
    Explanations

    adverbs used to emphasize a remarkable or significant quality

    oai_token-act-pair · gpt-3.5-turbo

    adjectives indicating a high degree of quality or uniqueness

    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
    icipated
    -0.82
    gang
    -0.71
    icip
    -0.69
    uese
    -0.66
     Cities
    -0.65
    ership
    -0.65
    lord
    -0.64
    glas
    -0.63
    ĺħ
    -0.62
    arta
    -0.62
    POSITIVE LOGITS
     LIMITED
    0.87
     absent
    0.80
    beit
    0.74
     unchanged
    0.74
     unaffected
    0.73
     coinc
    0.72
     noticeable
    0.71
    NESS
    0.71
     impressive
    0.71
     surprising
    0.68
    Activations Density 0.019%

    No Known Activations