© 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. 7-RES-JB
    11. 9319
    Prev
    Next
    INDEX
    Explanations

    terms related to structural aspects or qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to structural issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kin
    -0.86
    nery
    -0.82
    stretched
    -0.80
    rica
    -0.79
    kins
    -0.78
    renheit
    -0.77
    lance
    -0.77
    nen
    -0.77
    houses
    -0.76
    house
    -0.75
    POSITIVE LOGITS
    ized
    0.95
     integrity
    0.93
     disadvantages
    0.91
     components
    0.90
     weaknesses
    0.90
     impairment
    0.90
     barriers
    0.89
     elements
    0.88
     flaws
    0.87
     deficiencies
    0.87
    Activations Density 0.045%

    No Known Activations