© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7254
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types or properties of malt in context

    oai_token-act-pair · gpt-3.5-turbo

    references to malt in various contexts

    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
     Kaw
    -0.74
     FANTASY
    -0.74
    ITED
    -0.73
    hips
    -0.72
    BACK
    -0.70
     Electronic
    -0.69
    enhagen
    -0.69
    ockets
    -0.67
    TIME
    -0.67
    ILA
    -0.67
    POSITIVE LOGITS
    reatment
    1.24
    reated
    1.07
    ese
    0.97
     Malt
    0.96
    ophon
    0.96
     malt
    0.91
     whisky
    0.91
    ghazi
    0.90
    rose
    0.89
    anie
    0.89
    Activations Density 0.009%

    No Known Activations