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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18667
    Prev
    Next
    INDEX
    Explanations

    comparisons using similes

    oai_token-act-pair · gpt-3.5-turbo

    similes that compare experiences or objects to other things

    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
    idates
    -0.76
    amina
    -0.66
     independents
    -0.65
     SUPPORT
    -0.65
    andra
    -0.64
    Support
    -0.63
    emin
    -0.62
    çİĭ
    -0.62
    etheless
    -0.61
    RM
    -0.61
    POSITIVE LOGITS
     Gest
    0.75
     dise
    0.73
     sponge
    0.72
     magnet
    0.69
     steroids
    0.67
     goose
    0.66
    itaire
    0.66
     homework
    0.66
     drowning
    0.65
    worm
    0.65
    Activations Density 0.454%

    No Known Activations