© 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. 0-RES-JB
    6. 16685
    Prev
    Next
    INDEX
    Explanations

    mentions of Certificate Authorities (CAs) or related terms like "CA", "SSL", and "audit"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "CA," likely related to California or an associated entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lust
    -0.69
     stamina
    -0.68
     Sloven
    -0.67
     Wester
    -0.66
     Miz
    -0.66
     whist
    -0.65
     upt
    -0.65
     thunder
    -0.65
     Sieg
    -0.64
     Oprah
    -0.64
    POSITIVE LOGITS
    CA
    4.19
     CA
    1.92
    CO
    1.73
    ca
    1.60
    Ca
    1.51
    CC
    1.51
    Calif
    1.49
    CLA
    1.49
    CB
    1.43
    CS
    1.42
    Activations Density 0.007%

    No Known Activations