© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1523
    Prev
    Next
    INDEX
    Explanations

    statements related to recent events or developments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the arrival or introduction of new elements or ideas

    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
    isites
    -0.76
    tops
    -0.76
    isite
    -0.75
    ifi
    -0.73
    imon
    -0.72
    orst
    -0.71
    rendered
    -0.70
    ilion
    -0.70
    hemat
    -0.69
    icons
    -0.69
    POSITIVE LOGITS
     undone
    0.86
     forth
    0.82
     roaring
    0.81
     pains
    0.74
     revelations
    0.71
     havoc
    0.71
     tides
    0.70
     crashing
    0.69
    backs
    0.68
     Judgment
    0.66
    Activations Density 0.045%

    No Known Activations