© 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. 1-RES-JB
    11. 20366
    Prev
    Next
    INDEX
    Explanations

    last names with 'ac' followed by a high activation number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ac" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stur
    -0.87
    ĸļ
    -0.87
     Furious
    -0.75
     Continued
    -0.68
     Dare
    -0.66
     beware
    -0.66
     Desire
    -0.66
    è»
    -0.65
     Heck
    -0.64
     Kirst
    -0.64
    POSITIVE LOGITS
    rylic
    1.26
    ademic
    1.19
    oustic
    1.18
    ac
    1.06
    atech
    1.06
    celer
    1.05
    anth
    1.03
    acia
    1.03
    upuncture
    1.03
    adian
    0.96
    Activations Density 0.011%

    No Known Activations