© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 3999
    Prev
    Next
    INDEX
    Explanations

    spirit-related words

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'spirits' as they pertain to beverages or emotional states

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

    No Comments

    Negative Logits
    ded
    -0.74
     CFR
    -0.73
    artment
    -0.70
    jamin
    -0.69
    ãĥ³ãĤ¸
    -0.68
    iary
    -0.68
    efer
    -0.67
    advertisement
    -0.67
    ãĥª
    -0.67
    chini
    -0.66
    POSITIVE LOGITS
     spirits
    0.94
    pring
    0.88
    oshenko
    0.79
     exha
    0.78
    bane
    0.76
     whis
    0.72
    hell
    0.71
     veter
    0.70
     haunting
    0.69
     tremend
    0.68
    Activations Density 0.010%

    No Known Activations