© 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. 2-RES-JB
    11. 8089
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement and criminal activity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "SO" or phrases associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mark
    -0.70
    guard
    -0.70
    naires
    -0.68
    marks
    -0.67
    ikan
    -0.64
     envy
    -0.64
    endants
    -0.64
    percent
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.61
     revolving
    -0.61
    POSITIVE LOGITS
    FTWARE
    1.45
    othe
    1.10
    culus
    1.00
    arin
    0.89
    bered
    0.89
    oths
    0.88
    ooo
    0.87
    VER
    0.83
    OTH
    0.82
    BI
    0.81
    Activations Density 0.004%

    No Known Activations