© 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. 3-RES-JB
    11. 16165
    Prev
    Next
    INDEX
    Explanations

    keywords related to monetization and incentives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to monetization strategies and predatory practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.93
     Ago
    -0.74
     Absent
    -0.68
     TAMADRA
    -0.67
     Continued
    -0.66
     Sight
    -0.66
    endif
    -0.66
     Rite
    -0.65
    nesses
    -0.65
    cond
    -0.64
    POSITIVE LOGITS
     monet
    1.27
    izable
    1.06
    arily
    1.02
    isable
    0.89
    ization
    0.88
    ized
    0.88
    imet
    0.86
    vertising
    0.86
    VERTISEMENT
    0.85
    ised
    0.83
    Activations Density 0.009%

    No Known Activations