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. 19219
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming code, specifically involving database operations and console output

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or specific syntax related to programming code

    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
     conflic
    -0.97
     glim
    -0.88
     behavi
    -0.87
    ansk
    -0.84
     therap
    -0.83
     perspect
    -0.78
     veter
    -0.76
     confir
    -0.76
     enthusi
    -0.75
    ħĭ
    -0.72
    POSITIVE LOGITS
    html
    0.97
    prototype
    0.94
    length
    0.91
    internal
    0.90
    fn
    0.88
    mk
    0.86
    ini
    0.86
    NET
    0.83
    utils
    0.83
    mp
    0.82
    Activations Density 0.100%

    No Known Activations