© 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 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. 20672
    Prev
    Next
    INDEX
    Explanations

    words related to suggestions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    phrases questioning or challenging the status quo

    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
    photo
    -0.74
    ELD
    -0.72
    digit
    -0.70
    utch
    -0.68
    iple
    -0.66
    Reviewed
    -0.65
    chairs
    -0.64
    vor
    -0.63
    iHUD
    -0.61
    ItemTracker
    -0.61
    POSITIVE LOGITS
     indulge
    0.87
    ?]
    0.86
     emulate
    0.81
    itia
    0.79
     unleash
    0.77
     succumb
    0.74
     abolish
    0.74
     invoke
    0.74
     intervene
    0.74
     recreate
    0.73
    Activations Density 0.028%

    No Known Activations