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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 10431
    Prev
    Next
    INDEX
    Explanations

    In this case, the neuron seems to be looking for locations or terms related to the word "Dh" with a specific emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the character sequence that marks the end of a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berman
    -0.82
    essee
    -0.82
    plex
    -0.80
    ktop
    -0.80
    urally
    -0.79
    structed
    -0.75
    opausal
    -0.72
    imeter
    -0.69
    stadt
    -0.69
    Īè
    -0.66
    POSITIVE LOGITS
    ĪĴ
    1.04
    ouston
    0.91
    ा
    0.91
    onest
    0.79
    ulk
    0.78
    à¥
    0.75
    enger
    0.75
    awk
    0.73
    irst
    0.72
    ansom
    0.71
    Activations Density 0.044%

    No Known Activations