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. 13876
    Prev
    Next
    INDEX
    Explanations

    words related to the sensation of taste or physical sensations within the mouth

    oai_token-act-pair · gpt-3.5-turbo

    references to the mouth and related sensations

    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
    irements
    -0.67
     Investors
    -0.65
     subp
    -0.65
    udeb
    -0.64
     Athletics
    -0.64
     Myst
    -0.64
     Levi
    -0.63
     AA
    -0.61
     Monarch
    -0.61
    JM
    -0.61
    POSITIVE LOGITS
    piece
    1.37
    pieces
    1.26
    wash
    1.15
    parts
    1.13
    ful
    1.02
    ilage
    0.97
     lips
    0.95
     mouth
    0.89
    bone
    0.89
    poke
    0.89
    Activations Density 0.013%

    No Known Activations