© 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. 2368
    Prev
    Next
    INDEX
    Explanations

    exclamations prompting action or response

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "come"

    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
     Anthem
    -0.74
    uliffe
    -0.70
    imedia
    -0.65
    visors
    -0.65
    rating
    -0.64
    orsi
    -0.62
    osterone
    -0.62
    ording
    -0.61
    BF
    -0.61
    İĭ
    -0.60
    POSITIVE LOGITS
    backs
    1.11
     hither
    1.07
    upp
    0.87
    back
    0.79
    leon
    0.76
     join
    0.72
     true
    0.71
     forth
    0.71
     alive
    0.70
    true
    0.68
    Activations Density 0.040%

    No Known Activations