© 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. 9-RES-JB
    11. 2352
    Prev
    Next
    INDEX
    Explanations

    past tense verbs indicating hypothetical scenarios or unrealized possibilities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "had" and related past-tense constructions

    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
    advertisement
    -0.63
    ãģį
    -0.62
     neigh
    -0.62
    CAST
    -0.62
     ru
    -0.62
    女
    -0.61
     scrimmage
    -0.61
    ãĤ¨ãĥ«
    -0.60
    FTWARE
    -0.59
     sacrific
    -0.59
    POSITIVE LOGITS
     they
    0.83
    ering
    0.74
     he
    0.73
     it
    0.72
     there
    0.66
    wolves
    0.66
    cher
    0.65
    ered
    0.65
    soever
    0.64
    itia
    0.63
    Activations Density 0.105%

    No Known Activations