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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14186
    Prev
    Next
    INDEX
    Explanations

    references to governmental entities, particularly the United States government

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty or minimal content in the document

    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
    arella
    -0.68
     Chaser
    -0.63
     baseline
    -0.60
    pherd
    -0.59
     destro
    -0.58
    reon
    -0.54
     frontline
    -0.54
     logistical
    -0.53
     quotas
    -0.53
     gap
    -0.53
    POSITIVE LOGITS
    ;;;;;;;;;;;;
    0.71
    channelAvailability
    0.65
    erville
    0.61
    VILLE
    0.60
     Reincarnated
    0.59
    heng
    0.59
     fame
    0.59
    icides
    0.59
    =-=-=-=-
    0.58
     wherein
    0.58
    Activations Density 0.234%

    No Known Activations