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. 0-RES-JB
    6. 11218
    Prev
    Next
    INDEX
    Explanations

    the number "Five."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of specific numbers and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arch
    -0.72
     associated
    -0.72
     favor
    -0.71
     advice
    -0.69
     done
    -0.69
     related
    -0.69
     rather
    -0.68
     QC
    -0.67
     CC
    -0.66
     ed
    -0.65
    POSITIVE LOGITS
    Five
    2.68
    Four
    2.59
    Three
    2.38
    Eight
    2.27
    Six
    2.27
    Seven
    2.26
    Nine
    2.25
    Two
    1.98
    Twenty
    1.96
    Ten
    1.92
    Activations Density 0.024%

    No Known Activations