© 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. 7-RES-JB
    11. 1565
    Prev
    Next
    INDEX
    Explanations

    action words suggesting consideration or specific tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest recommendations or advice

    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
    indle
    -0.70
    DX
    -0.66
    ynthesis
    -0.65
    ille
    -0.63
    idy
    -0.63
    ilian
    -0.62
    opl
    -0.61
    ophone
    -0.60
     VID
    -0.58
    ophobia
    -0.57
    POSITIVE LOGITS
     consider
    0.82
     reconsider
    0.75
    EStream
    0.73
     advis
    0.72
     rethink
    0.71
    ij士
    0.69
    abl
    0.69
    gotten
    0.68
    )=(
    0.68
    vised
    0.67
    Activations Density 0.080%

    No Known Activations