© 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. 3-RES-JB
    11. 1759
    Prev
    Next
    INDEX
    Explanations

    references to physical violence such as assault and mugging

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "mug" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISION
    -0.77
    edient
    -0.72
     Virgin
    -0.70
    Domin
    -0.69
    ×Ļ×
    -0.68
    ISE
    -0.68
    IGH
    -0.67
     Doctrine
    -0.66
    ipher
    -0.66
    cision
    -0.64
    POSITIVE LOGITS
     mug
    1.12
    gers
    1.11
    shots
    1.06
    ging
    1.02
    shot
    0.98
    ger
    0.96
    atures
    0.92
    ged
    0.88
    glers
    0.86
    gery
    0.84
    Activations Density 0.007%

    No Known Activations