Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4041
    Prev
    Next
    INDEX
    Explanations

    sentences with repetitive words or phrases like "talk and talk and talk" or "bang, bang, bang"

    oai_token-act-pair · gpt-3.5-turbo

    strong discussions around brands and consumerism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seiz
    -0.67
     cous
    -0.63
     Feder
    -0.56
    conservancy
    -0.55
     apr
    -0.55
    illon
    -0.55
    activity
    -0.54
    Dialog
    -0.54
     Pis
    -0.53
    TPS
    -0.52
    POSITIVE LOGITS
     â̦
    0.89
    !!!!
    0.86
     etc
    0.83
    !!!!!
    0.82
    oooo
    0.82
    oooooooo
    0.80
     ..............
    0.79
     ...
    0.78
     ..
    0.77
    !!!
    0.76
    Activations Density 0.202%

    No Known Activations