© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16079
    Prev
    Next
    INDEX
    Explanations

    words related to the utilization or analysis of tools or technology

    oai_token-act-pair · gpt-3.5-turbo

    references to utility and analysis in various contexts

    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
     VIDEOS
    -0.82
    OHN
    -0.76
    Shot
    -0.74
     Carlson
    -0.73
    clerosis
    -0.70
    meyer
    -0.68
    eah
    -0.68
    thal
    -0.67
     Russo
    -0.66
    RESULTS
    -0.64
    POSITIVE LOGITS
    £
    1.07
     Whilst
    0.96
     tyres
    0.95
     tyre
    0.95
     analyse
    0.93
     programmes
    0.92
     defences
    0.90
     £
    0.88
     programme
    0.87
    colour
    0.86
    Activations Density 0.357%

    No Known Activations