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. 14413
    Prev
    Next
    INDEX
    Explanations

    terms related to instruction manuals or processes

    oai_token-act-pair · gpt-3.5-turbo

    references to "manual" in various contexts

    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
    apest
    -0.82
    nces
    -0.74
    ween
    -0.72
    acious
    -0.70
    ymes
    -0.70
    mary
    -0.70
    our
    -0.70
    orative
    -0.68
    reek
    -0.68
    rug
    -0.68
    POSITIVE LOGITS
     dexterity
    0.98
     transmission
    0.90
     typew
    0.90
     override
    0.79
     exha
    0.76
     laborers
    0.74
     transmissions
    0.73
     circ
    0.73
     readable
    0.73
     induction
    0.71
    Activations Density 0.014%

    No Known Activations