© 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. 9-RES-JB
    11. 7420
    Prev
    Next
    INDEX
    Explanations

    words related to movement and activity

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and related forms of action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTOS
    -0.74
    gments
    -0.68
    >[
    -0.66
    ema
    -0.66
    ãĥ¤
    -0.65
    gment
    -0.65
    alls
    -0.62
     pronounced
    -0.60
    catentry
    -0.59
     provocation
    -0.58
    POSITIVE LOGITS
     around
    1.06
     hither
    0.95
     across
    0.95
     away
    0.94
     endlessly
    0.94
     wildly
    0.92
     downhill
    0.86
     happily
    0.85
    around
    0.85
     along
    0.85
    Activations Density 0.296%

    No Known Activations