© 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. 8-RES-JB
    11. 7075
    Prev
    Next
    INDEX
    Explanations

    instances where an action is being performed or a comparison is made

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing variations of the verb "do" and "did."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cipled
    -0.69
    urst
    -0.63
    Published
    -0.60
    asta
    -0.60
    iken
    -0.59
     SAR
    -0.58
    ussed
    -0.58
     Provided
    -0.57
    ouple
    -0.57
    bent
    -0.57
    POSITIVE LOGITS
    pez
    0.86
    ettings
    0.72
    zed
    0.72
    aughters
    0.68
    zing
    0.67
     mosqu
    0.66
    jet
    0.57
    llor
    0.57
    Downloadha
    0.57
     whenever
    0.56
    Activations Density 0.056%

    No Known Activations