© 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. 3-RES-JB
    11. 21286
    Prev
    Next
    INDEX
    Explanations

    words related to a period of consecutive successes or wins

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "streak" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤº
    -0.72
    gency
    -0.69
    resources
    -0.67
    ACTED
    -0.67
    hospital
    -0.67
    posing
    -0.66
    poses
    -0.65
     aid
    -0.64
    remlin
    -0.63
    abad
    -0.63
    POSITIVE LOGITS
     streak
    1.37
     streaks
    1.01
    manship
    0.87
    iness
    0.84
    icity
    0.78
    uous
    0.75
    mates
    0.72
     Mania
    0.69
    yk
    0.66
    FTWARE
    0.65
    Activations Density 0.013%

    No Known Activations