© 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. 12899
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to probability and statistics

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and symbols

    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
    terday
    -0.93
     destro
    -0.87
    ascus
    -0.80
    waukee
    -0.74
    anmar
    -0.74
    abwe
    -0.72
    sters
    -0.71
    inois
    -0.69
     Valent
    -0.68
     Ago
    -0.65
    POSITIVE LOGITS
    wcsstore
    1.10
    \\\\\\\\\\\\\\\\
    0.93
    frac
    0.87
    sum
    0.84
    ŃĶ
    0.84
    times
    0.83
    SpaceEngineers
    0.82
     \
    0.81
    relative
    0.79
    Ħ¢
    0.79
    Activations Density 0.009%

    No Known Activations