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. 8-RES-JB
    6. 96
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the domain "co.uk"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhy
    -0.64
     guiActiveUn
    -0.62
    ById
    -0.62
     guiActive
    -0.61
     shaving
    -0.60
    Bottom
    -0.58
    Pin
    -0.57
     Advocate
    -0.57
     caucuses
    -0.56
     steroids
    -0.56
    POSITIVE LOGITS
    uk
    1.20
    nz
    1.12
    za
    0.96
    jp
    0.93
    merce
    0.89
    ucl
    0.87
    gov
    0.87
    kr
    0.86
    dk
    0.84
    fecture
    0.82
    Activations Density 0.047%

    No Known Activations