© 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. 2-RES-JB
    11. 1972
    Prev
    Next
    INDEX
    Explanations

    topics related to news events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to tragedies or significant events related to migrants or social issues

    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
    quist
    -0.78
    aunder
    -0.72
    acea
    -0.69
    esville
    -0.68
     Greenwald
    -0.65
    raised
    -0.63
    Downloadha
    -0.62
     Bret
    -0.62
    effect
    -0.62
     Advocate
    -0.60
    POSITIVE LOGITS
    TY
    1.44
     IMAGES
    1.38
    ENCY
    0.90
    MORE
    0.83
     Doodle
    0.79
    URE
    0.77
    MU
    0.74
     Tart
    0.71
    APE
    0.71
    yss
    0.71
    Activations Density 0.006%

    No Known Activations