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. 15471
    Prev
    Next
    INDEX
    Explanations

    names containing the substring "jo"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jo."

    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
    binary
    -0.70
    rified
    -0.69
    flies
    -0.68
    cream
    -0.64
    ãĥķãĤ©
    -0.63
    天
    -0.63
     bombard
    -0.63
    nat
    -0.62
    opian
    -0.61
    tle
    -0.61
    POSITIVE LOGITS
    jo
    1.13
    vernment
    1.03
    aquin
    1.02
    unction
    0.92
    zzo
    0.88
    quez
    0.81
    Desk
    0.80
    Jo
    0.80
    atana
    0.79
    zai
    0.78
    Activations Density 0.008%

    No Known Activations