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. 18111
    Prev
    Next
    INDEX
    Explanations

    references to device support or incompatibility issues

    oai_token-act-pair · gpt-3.5-turbo

    mentions of devices and browser compatibility

    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
    laus
    -0.68
    ractions
    -0.65
    ornia
    -0.65
    fin
    -0.65
    etts
    -0.64
    alore
    -0.63
    iton
    -0.63
    neapolis
    -0.63
    glomer
    -0.62
     Nights
    -0.61
    POSITIVE LOGITS
     device
    0.71
     unsupported
    0.71
    taboola
    0.71
    CTV
    0.68
     Xperia
    0.68
     devices
    0.67
     WATCHED
    0.66
     charger
    0.64
    washer
    0.63
     caption
    0.63
    Activations Density 0.007%

    No Known Activations