© 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. 20894
    Prev
    Next
    INDEX
    Explanations

    mentions of being a fan or enthusiast

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a strong emphasis on a particular point or subject

    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
    ¬¼
    -0.85
    UTC
    -0.75
    enary
    -0.73
    vind
    -0.69
    acio
    -0.68
    osite
    -0.66
    OGR
    -0.64
    ELD
    -0.64
    ['
    -0.63
    anqu
    -0.62
    POSITIVE LOGITS
     congr
    1.06
     congratulations
    1.01
     chances
    0.93
     please
    0.91
     beware
    0.82
     PLEASE
    0.78
    please
    0.77
    tein
    0.77
     you
    0.71
     check
    0.70
    Activations Density 0.172%

    No Known Activations