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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8389
    Prev
    Next
    INDEX
    Explanations

    information about releases or installments in series or franchises

    oai_token-act-pair · gpt-3.5-turbo

    references to film franchises and their installments

    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
    nces
    -0.89
     nevertheless
    -0.77
    entimes
    -0.71
     elsewhere
    -0.69
    utterstock
    -0.68
    ews
    -0.67
    vana
    -0.66
    acon
    -0.65
    inem
    -0.65
    onday
    -0.65
    POSITIVE LOGITS
     trilogy
    1.18
     series
    1.09
    series
    0.99
     saga
    0.98
     Series
    0.86
    Series
    0.81
     dynasty
    0.74
     Chain
    0.72
     countdown
    0.72
     Trilogy
    0.72
    Activations Density 0.289%

    No Known Activations