© 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. 11-RES-JB
    11. 7542
    Prev
    Next
    INDEX
    Explanations

    contact information including phone numbers and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    contact information details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \">
    -0.68
    Pg
    -0.65
    asus
    -0.64
    ICAN
    -0.61
     [&
    -0.60
    DCS
    -0.60
    )].
    -0.59
    ))
    -0.58
    ————
    -0.58
    )).
    -0.58
    POSITIVE LOGITS
    ר
    0.64
    ãĥķãĤ©
    0.58
    aution
    0.56
     metic
    0.55
    ש
    0.54
     exting
    0.54
     skelet
    0.54
    cloneembedreportprint
    0.52
     destro
    0.52
    ially
    0.52
    Activations Density 0.067%

    No Known Activations