© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 18481
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for mentions of a specific name, possibly "Paganini"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of a specific substring or sequence of letters in various names and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \\\\\\\\
    -0.81
    phe
    -0.77
    rill
    -0.72
    lisher
    -0.72
    wick
    -0.71
    ility
    -0.71
    spin
    -0.71
    pir
    -0.69
    ridges
    -0.69
    lon
    -0.69
    POSITIVE LOGITS
    Äĩ
    1.25
    ère
    1.13
    otti
    1.10
    zzi
    1.07
    arella
    0.97
    zzo
    0.92
    ucci
    0.91
    orno
    0.91
    otto
    0.89
    ennes
    0.88
    Activations Density 0.107%

    No Known Activations