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. 13575
    Prev
    Next
    INDEX
    Explanations

    words related to the Olympics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Olympic Games and related locations

    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
    TEXTURE
    -0.70
     Bakr
    -0.63
     penetrating
    -0.61
    xual
    -0.59
     fitting
    -0.59
    vec
    -0.59
    FIELD
    -0.58
     tongue
    -0.56
    ño
    -0.56
     corrections
    -0.56
    POSITIVE LOGITS
    ics
    1.27
    ique
    1.24
    icism
    1.22
    icians
    1.20
    ications
    1.15
    ically
    1.14
    ic
    1.14
    ication
    1.13
    icate
    1.12
    icist
    1.11
    Activations Density 0.041%

    No Known Activations