© 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. 9-RES-JB
    11. 20846
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to specific establishments or locations that are popular or significant

    oai_token-act-pair · gpt-3.5-turbo

    references to staple foods or essential elements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    claimer
    -0.70
     equivalents
    -0.66
     equivalent
    -0.65
     terminated
    -0.64
    gency
    -0.64
     equival
    -0.64
    arent
    -0.63
    quila
    -0.63
    qus
    -0.63
    iliated
    -0.63
    POSITIVE LOGITS
     locals
    0.76
     tourists
    0.73
    sports
    0.73
     environmentalists
    0.73
     collectors
    0.72
     tourist
    0.71
     enthusiasts
    0.69
     festive
    0.68
     travelers
    0.68
     Latter
    0.67
    Activations Density 0.317%

    No Known Activations