© 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. 20793
    Prev
    Next
    INDEX
    Explanations

    phrases indicating options or alternatives

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various contexts

    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
     understandably
    -0.68
     Kavanaugh
    -0.56
     redes
    -0.55
     Ramos
    -0.55
     enormously
    -0.53
     Revis
    -0.52
     Bigfoot
    -0.52
     foremost
    -0.51
    APTER
    -0.51
    axies
    -0.51
    POSITIVE LOGITS
    abouts
    1.10
    Else
    1.06
    depending
    0.88
     equivalent
    0.84
    phans
    0.82
    acle
    0.82
    chard
    0.79
    nam
    0.78
     alternatively
    0.72
    omever
    0.71
    Activations Density 0.272%

    No Known Activations