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. 24108
    Prev
    Next
    INDEX
    Explanations

    questions often related to personal opinions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    questions and statements related to access and concerns regarding health and societal issues

    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
    itol
    -0.72
     Chevron
    -0.61
    ICLE
    -0.60
    CCC
    -0.60
    perties
    -0.59
     CoC
    -0.59
    pty
    -0.59
     civilized
    -0.59
     civilization
    -0.59
     Cecil
    -0.58
    POSITIVE LOGITS
     GOODMAN
    0.82
    anga
    0.69
    kamp
    0.69
    Interview
    0.68
    laughs
    0.67
     studio
    0.67
     largeDownload
    0.63
     Studio
    0.62
     hiatus
    0.62
    olver
    0.62
    Activations Density 0.182%

    No Known Activations