© 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. 1215
    Prev
    Next
    INDEX
    Explanations

    the word "Pill" along with a numerical value associated with it

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific item associated with medication

    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
    EMENT
    -0.77
    rily
    -0.66
    IAL
    -0.65
    CEPT
    -0.64
    ~~~~
    -0.63
    ALT
    -0.63
    ially
    -0.60
    âĸ¬
    -0.60
    eers
    -0.59
    ELY
    -0.59
    POSITIVE LOGITS
    ows
    1.44
    oried
    1.24
    owed
    1.12
    ipop
    1.01
    ow
    1.00
    iard
    0.98
    sworth
    0.94
    sburgh
    0.93
    OWS
    0.93
    ars
    0.93
    Activations Density 0.094%

    No Known Activations