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

    Neuronpedia

    Jacobian LensNEW
    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. 16022
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or criminal activities involving communication

    oai_token-act-pair · gpt-3.5-turbo

    co-occurrences of the word "and" with various other terms related to communications and investigations

    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
    elo
    -0.70
    wic
    -0.66
    ondon
    -0.66
    imester
    -0.66
    arak
    -0.65
    ummer
    -0.63
    WR
    -0.63
    ukong
    -0.62
    urch
    -0.62
    Manager
    -0.61
    POSITIVE LOGITS
     other
    1.13
     assorted
    0.95
     others
    0.81
     possibly
    0.79
     various
    0.75
     occasional
    0.73
     unspecified
    0.72
     logistical
    0.71
     several
    0.69
     elsewhere
    0.68
    Activations Density 0.469%

    No Known Activations