© 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 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. 7-RES-JB
    11. 5774
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to taking action toward a certain commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "commit" and its variations, especially in relation to serious actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     complexion
    -0.69
     Flavoring
    -0.68
    iewicz
    -0.66
    ****************
    -0.65
    WARN
    -0.64
    atin
    -0.64
     Remastered
    -0.63
    >]
    -0.63
    nz
    -0.61
     Cheong
    -0.61
    POSITIVE LOGITS
     suicide
    0.98
    utions
    0.80
    itent
    0.78
    ruction
    0.77
     adultery
    0.77
    forestation
    0.75
    commit
    0.72
     offences
    0.70
    acts
    0.70
    icts
    0.70
    Activations Density 0.033%

    No Known Activations