© 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. 20911
    Prev
    Next
    INDEX
    Explanations

    quantitative values mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and statistical metrics

    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
     Situation
    -0.73
     ART
    -0.70
    Oper
    -0.68
     Rein
    -0.68
     Sear
    -0.66
     Bellev
    -0.65
    ourge
    -0.63
     Beaver
    -0.63
    odynam
    -0.62
    clinical
    -0.61
    POSITIVE LOGITS
     rpm
    0.83
    mb
    0.80
     yuan
    0.80
     RPM
    0.77
     cents
    0.75
    taboola
    0.73
    uters
    0.73
    ¼
    0.70
     mins
    0.69
    000
    0.69
    Activations Density 0.181%

    No Known Activations