© 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 EvalsExportsinterp-engineNEWAPI 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. 13209
    Prev
    Next
    INDEX
    Explanations

    mentions of steps or actions needed to progress towards a goal or achieve a result

    oai_token-act-pair · gpt-3.5-turbo

    references to sequential actions or processes

    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
    rums
    -0.81
    arus
    -0.72
     Crate
    -0.67
    inately
    -0.64
    olls
    -0.64
    ycle
    -0.64
     sweats
    -0.62
    eer
    -0.62
     Moose
    -0.61
    ecause
    -0.61
    POSITIVE LOGITS
     forward
    1.13
     toward
    1.11
     towards
    1.10
    iblings
    1.03
    steps
    1.00
    step
    0.94
    hens
    0.93
     forwards
    0.90
     backward
    0.86
    daughter
    0.83
    Activations Density 0.036%

    No Known Activations