© 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. 21154
    Prev
    Next
    INDEX
    Explanations

    verbs in present tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the current status or condition of subjects

    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
    fts
    -0.58
    aunder
    -0.57
    WER
    -0.56
    Newsletter
    -0.55
    obbies
    -0.55
    igent
    -0.55
    ":[{"
    -0.55
    heny
    -0.54
     Photographer
    -0.54
     Lawn
    -0.53
    POSITIVE LOGITS
     finally
    1.23
     nearing
    1.20
     now
    1.19
     fading
    1.13
     progressing
    1.08
     disappearing
    1.07
     returning
    1.07
     still
    1.05
     crumbling
    1.04
     gone
    1.03
    Activations Density 0.330%

    No Known Activations