© 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. 9-RES-JB
    11. 7236
    Prev
    Next
    INDEX
    Explanations

    words related to final outcomes or conclusions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of finality or outcomes

    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
    Normally
    -0.74
    RN
    -0.67
     ordinarily
    -0.66
     otherwise
    -0.66
     regularly
    -0.65
     ASAP
    -0.64
     Recently
    -0.64
     Normally
    -0.62
     previously
    -0.62
     normally
    -0.61
    POSITIVE LOGITS
     deciding
    0.84
     unsuccessful
    0.82
     boils
    0.75
     decided
    0.74
     futile
    0.73
     decide
    0.72
     succeeded
    0.71
     responsible
    0.71
    apor
    0.70
     proved
    0.68
    Activations Density 0.035%

    No Known Activations