© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 8544
    Prev
    Next
    INDEX
    Explanations

    references to "Botanical Gardens"

    oai_token-act-pair · gpt-3.5-turbo

    references to "bot" or "botanical" themes

    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
    dress
    -0.88
    â̦â̦â̦â̦â̦â̦â̦â̦
    -0.72
    PLIED
    -0.65
    mund
    -0.62
    vironment
    -0.61
    separ
    -0.60
    ividual
    -0.59
    baugh
    -0.58
     Trib
    -0.58
    xual
    -0.57
    POSITIVE LOGITS
    anical
    1.35
    anic
    1.03
    ania
    0.99
    anie
    0.94
     Bot
    0.94
    rol
    0.88
    any
    0.88
    atoes
    0.87
    zeb
    0.86
    wana
    0.85
    Activations Density 0.011%

    No Known Activations