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. 14879
    Prev
    Next
    INDEX
    Explanations

    words related to physical body parts, specifically the throat

    oai_token-act-pair · gpt-3.5-turbo

    references to the throat and related injuries or conditions

    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
    udeb
    -0.76
    atern
    -0.66
     CES
    -0.65
     Athlet
    -0.63
     Sigma
    -0.62
     mete
    -0.59
    CAST
    -0.58
    Amazon
    -0.58
    notation
    -0.56
     Woodward
    -0.56
    POSITIVE LOGITS
     throat
    1.25
     throats
    1.24
     slit
    1.01
    bone
    0.96
    pipe
    0.95
    ħĭ
    0.91
     cavity
    0.89
    bones
    0.86
    piece
    0.84
    lines
    0.81
    Activations Density 0.007%

    No Known Activations