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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3239
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Gerry" at varying activations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "berry" and its variations

    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
    agos
    -0.90
    isting
    -0.76
    ahime
    -0.75
    aepernick
    -0.75
    iesta
    -0.75
    agonist
    -0.75
    icago
    -0.75
    awar
    -0.74
    ouch
    -0.74
    anooga
    -0.73
    POSITIVE LOGITS
    mand
    1.05
    mite
    0.79
    erry
    0.78
    ments
    0.77
     Gerry
    0.76
    mph
    0.74
    bye
    0.73
    nda
    0.72
    llo
    0.71
    ng
    0.70
    Activations Density 0.018%

    No Known Activations