© 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. 24064
    Prev
    Next
    INDEX
    Explanations

    phrases related to common procedures or practices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social norms and customary practices

    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
    itamin
    -0.66
    pell
    -0.64
    kamp
    -0.64
     Proposition
    -0.61
     concentrate
    -0.60
     burnt
    -0.60
    atto
    -0.60
     Chandra
    -0.59
     finished
    -0.57
     Bern
    -0.57
    POSITIVE LOGITS
    pmwiki
    1.02
    entimes
    0.89
     occurrence
    0.83
    rences
    0.82
    Į
    0.79
    fare
    0.77
     occurrences
    0.77
    usual
    0.76
    velt
    0.75
    alis
    0.73
    Activations Density 0.207%

    No Known Activations