Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10635
    Prev
    Next
    INDEX
    Explanations

    numbers that are part of a sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to the number "ten."

    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
    Downloadha
    -0.72
    hammad
    -0.67
    igslist
    -0.66
    ller
    -0.59
     DRAG
    -0.59
     Indust
    -0.59
    ramid
    -0.58
    HY
    -0.58
    LY
    -0.57
    azo
    -0.57
    POSITIVE LOGITS
    aciously
    1.25
    acious
    1.21
    acity
    1.14
    uous
    1.13
     thousand
    1.06
    uously
    1.04
    fold
    1.04
    eenth
    1.02
    ured
    1.02
    ieth
    0.97
    Activations Density 0.010%

    No Known Activations