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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 13846
    Prev
    Next
    INDEX
    Explanations

    facts or statistics related to research and surveys

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical findings or estimates related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comrade
    -0.82
    enment
    -0.77
     yours
    -0.74
    }}}
    -0.70
     comrades
    -0.70
    quished
    -0.67
    swer
    -0.67
     tv
    -0.66
    oleon
    -0.66
     glory
    -0.64
    POSITIVE LOGITS
     overest
    0.97
     disproportionately
    0.89
     "â̦
    0.88
     clustered
    0.86
     significantly
    0.85
     outper
    0.85
    ificantly
    0.84
     median
    0.84
     "[
    0.82
     underestimated
    0.79
    Activations Density 0.740%

    No Known Activations