© 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. 14884
    Prev
    Next
    INDEX
    Explanations

    references to mushrooms

    oai_token-act-pair · gpt-3.5-turbo

    references to mushrooms and fungi

    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
    mand
    -0.71
    NEY
    -0.70
    points
    -0.69
    PUT
    -0.68
    avier
    -0.65
    vent
    -0.64
    pless
    -0.63
    âĸ¬âĸ¬
    -0.63
     clipboard
    -0.61
    verbal
    -0.61
    POSITIVE LOGITS
     mushrooms
    1.13
    ccoli
    1.05
     spores
    0.96
     mushroom
    0.92
    lio
    0.89
    atoes
    0.88
     fungi
    0.88
    cules
    0.84
    roots
    0.84
     Mush
    0.83
    Activations Density 0.016%

    No Known Activations