© 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. 8-RES-JB
    11. 19409
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uniqueness or differentiation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize uniqueness or distinguishing characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     draining
    -0.69
     Instr
    -0.68
     drained
    -0.67
     vomiting
    -0.66
     blackmail
    -0.65
     fax
    -0.62
     entertained
    -0.62
    gres
    -0.62
     itching
    -0.62
     coerced
    -0.62
    POSITIVE LOGITS
     uniqueness
    0.85
    undrum
    0.79
    arily
    0.78
     insofar
    0.78
    emale
    0.73
     pedigree
    0.73
    allery
    0.71
    ilial
    0.71
     distinguishes
    0.71
     distinguishing
    0.71
    Activations Density 0.454%

    No Known Activations