© 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. 24422
    Prev
    Next
    INDEX
    Explanations

    action words indicating addressing or dealing with various issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    references to addressing or resolving significant issues

    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
    urt
    -0.82
    akin
    -0.75
    abet
    -0.71
    handler
    -0.64
    appointed
    -0.58
    aft
    -0.58
    aver
    -0.58
     subp
    -0.57
     Sabha
    -0.57
    Render
    -0.57
    POSITIVE LOGITS
     tackle
    0.85
    ãĥ¯ãĥ³
    0.81
    rolet
    0.79
    tackle
    0.78
     tackling
    0.77
     tackles
    0.74
    iton
    0.72
    ahime
    0.72
    cture
    0.70
    cliffe
    0.69
    Activations Density 0.016%

    No Known Activations