© 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. 24070
    Prev
    Next
    INDEX
    Explanations

    Latin characters with accent marks

    oai_token-act-pair · gpt-3.5-turbo

    numerical or coded representations, possibly index or reference data in a list format

    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
    iott
    -0.65
    bert
    -0.63
     thirsty
    -0.63
    atten
    -0.60
    bringer
    -0.59
     bour
    -0.59
    marks
    -0.59
     veter
    -0.57
     downs
    -0.57
    sb
    -0.56
    POSITIVE LOGITS
    âĵĺ
    0.91
    ³³³³
    0.83
    Introduced
    0.80
    ================================================================
    0.77
    ³³³
    0.75
    ³³³³³³³³³³³³³³³³
    0.71
    NES
    0.70
    âķIJâķIJ
    0.70
    ³³³³³³³³
    0.69
    052
    0.69
    Activations Density 0.128%

    No Known Activations