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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17205
    Prev
    Next
    INDEX
    Explanations

    mentions of leaves

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "leaf" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDATE
    -0.71
    CLUS
    -0.67
    senal
    -0.65
    alty
    -0.64
    nels
    -0.63
     attackers
    -0.63
    ogene
    -0.62
    afort
    -0.61
    ENTION
    -0.61
     incumb
    -0.60
    POSITIVE LOGITS
    let
    1.29
    lets
    1.19
    leaf
    1.03
    leted
    1.00
    iard
    0.95
     leaf
    0.93
    lete
    0.91
    ho
    0.89
    overs
    0.87
    letes
    0.87
    Activations Density 0.046%

    No Known Activations