© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 405
    Prev
    Next
    INDEX
    Explanations

    words related to advertisements or commercial promotions

    oai_token-act-pair · gpt-3.5-turbo

    words related to "vert" and "pert," likely indicating a focus on references to personal identities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    daq
    -0.83
    ptive
    -0.75
    AW
    -0.68
    ntax
    -0.66
    cloth
    -0.65
    ntil
    -0.65
    prus
    -0.63
    tone
    -0.62
    natureconservancy
    -0.62
    illac
    -0.62
    POSITIVE LOGITS
    arget
    0.90
    ract
    0.87
    ibles
    0.86
    ucky
    0.86
    aneous
    0.86
    IBLE
    0.83
    ible
    0.80
    rees
    0.79
    itles
    0.78
    raction
    0.78
    Activations Density 0.090%

    No Known Activations