© 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. 4-RES-JB
    11. 22311
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Dav" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dav," indicating a focus on a specific location or entity

    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
    ACTED
    -0.75
    TRY
    -0.68
    ãĥĺãĥ©
    -0.65
     occup
    -0.64
    CLASS
    -0.64
    Gaza
    -0.63
    LOAD
    -0.63
     Fired
    -0.62
    LESS
    -0.61
    Ground
    -0.60
    POSITIVE LOGITS
    isco
    0.95
    iral
    0.93
    ildo
    0.93
    illon
    0.90
    isson
    0.88
    inas
    0.88
    ilo
    0.88
    inelli
    0.88
    enture
    0.87
    ict
    0.87
    Activations Density 0.006%

    No Known Activations