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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 13878
    Prev
    Next
    INDEX
    Explanations

    mentions of new additions or enhancements

    oai_token-act-pair · gpt-3.5-turbo

    references to new additions or improvements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zees
    -0.72
    rior
    -0.72
    zh
    -0.71
    zee
    -0.69
    rpm
    -0.66
    raz
    -0.65
    rolled
    -0.64
    bis
    -0.63
    yah
    -0.63
    robe
    -0.61
    POSITIVE LOGITS
    endum
    0.96
    xual
    0.84
    xon
    0.79
    ition
    0.79
    verted
    0.78
     thereto
    0.76
     Flavoring
    0.75
     insult
    0.71
    itives
    0.70
    itious
    0.68
    Activations Density 0.038%

    No Known Activations