© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 6543
    Prev
    Next
    INDEX
    Explanations

    numbers related to technical specifications or measurements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 32 associated with various contexts or entities

    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
    ĸļ
    -1.02
    andise
    -0.90
    ItemTracker
    -0.87
    aken
    -0.87
    amaru
    -0.86
    atchewan
    -0.84
    raints
    -0.82
    icago
    -0.80
    =-=-
    -0.80
    atre
    -0.80
    POSITIVE LOGITS
    nd
    1.03
    holm
    0.82
    00
    0.81
    50
    0.75
    80
    0.75
    LECT
    0.73
    384
    0.72
    ND
    0.70
    bit
    0.70
    VICE
    0.68
    Activations Density 0.014%

    No Known Activations