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. 11798
    Prev
    Next
    INDEX
    Explanations

    the word "body" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to "somebody" or variations thereof, indicating a focus on people in general

    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
    ring
    -0.76
    interstitial
    -0.71
    orses
    -0.65
    ozo
    -0.65
     QR
    -0.65
    eeds
    -0.63
    otes
    -0.63
    Ore
    -0.61
     precip
    -0.61
    utenberg
    -0.61
    POSITIVE LOGITS
     else
    1.28
    Else
    1.12
    else
    1.11
     Else
    1.01
     EL
    0.85
    body
    0.82
     alike
    0.80
     interviewed
    0.76
    theless
    0.75
     Bastard
    0.73
    Activations Density 0.033%

    No Known Activations