© 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. 24173
    Prev
    Next
    INDEX
    Explanations

    names of individuals in the context of employment, appointments, or acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    specific names and entities associated with sports figures and teams

    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
    endered
    -0.69
    ieves
    -0.69
    aunder
    -0.67
    =-=-=-=-
    -0.66
     âĶľâĶĢâĶĢ
    -0.65
    enders
    -0.63
    ":[{"
    -0.63
    ggles
    -0.63
    urized
    -0.62
    adders
    -0.61
    POSITIVE LOGITS
     agreeing
    1.24
     estimating
    1.22
     pledging
    1.19
     declaring
    1.19
     eyeing
    1.17
     announcing
    1.16
     occupying
    1.16
     topping
    1.16
     gearing
    1.15
     predicting
    1.15
    Activations Density 0.218%

    No Known Activations