© 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 EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 23703
    Prev
    Next
    INDEX
    Explanations

    words related to value, representation, and development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to valuation and representation

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

    No Comments

    Negative Logits
     Feinstein
    -0.69
    rir
    -0.67
    Plex
    -0.62
    APTER
    -0.61
     Rowling
    -0.60
    Party
    -0.60
    erva
    -0.58
     Literary
    -0.58
     abiding
    -0.58
     liberating
    -0.55
    POSITIVE LOGITS
    nesses
    0.89
    glers
    0.79
     glances
    0.71
     Opportun
    0.67
     (<
    0.67
    ealous
    0.67
     spoiled
    0.67
     expectations
    0.65
     stereotypes
    0.64
    WARE
    0.63
    Activations Density 0.093%

    No Known Activations