Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13849
    Prev
    Next
    INDEX
    Explanations

    the word "Dav" followed by either a single digit or the digits "os" and sometimes followed by additional characters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Davao."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.70
    ©¶æ
    -0.64
    PDATE
    -0.64
     occup
    -0.64
     electric
    -0.62
     Fired
    -0.62
     caption
    -0.61
    TRY
    -0.60
    WAYS
    -0.59
    CLASS
    -0.59
    POSITIVE LOGITS
    inas
    0.98
    isco
    0.98
    ildo
    0.97
    iral
    0.96
    illon
    0.93
    inelli
    0.93
    ict
    0.91
    isson
    0.90
    olla
    0.88
    oker
    0.88
    Activations Density 0.012%

    No Known Activations