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. 9-RES-JB
    6. 7649
    Prev
    Next
    INDEX
    Explanations

    mentions of "samples" or "sample size" in a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of sample size in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModLoader
    -0.78
    lesiastical
    -0.72
    lvl
    -0.69
    standing
    -0.68
     marqu
    -0.63
    Tony
    -0.63
    lisher
    -0.63
    les
    -0.63
    die
    -0.63
    CLASSIFIED
    -0.62
    POSITIVE LOGITS
    meal
    0.84
     sizes
    0.80
    icles
    0.78
     sample
    0.78
    atter
    0.76
     size
    0.76
    ographic
    0.74
     samples
    0.73
     collected
    0.73
     thereof
    0.72
    Activations Density 0.045%

    No Known Activations