© 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. 10982
    Prev
    Next
    INDEX
    Explanations

    references to the word "honey."

    oai_token-act-pair · gpt-3.5-turbo

    references to honey

    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
    uers
    -0.89
    aneous
    -0.87
    ative
    -0.84
    ATIONS
    -0.82
    aneously
    -0.81
    ŃĶ
    -0.76
    osure
    -0.75
    oppable
    -0.74
    utsche
    -0.71
    andals
    -0.70
    POSITIVE LOGITS
    moon
    1.32
    bees
    1.09
    bee
    1.08
    comb
    1.06
     bee
    0.98
     Bee
    0.91
     Honey
    0.90
    oney
    0.88
     honey
    0.85
    flake
    0.83
    Activations Density 0.004%

    No Known Activations