© 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. 1-RES-JB
    6. 24072
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a specific person named Sol

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Sol."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shapeshifter
    -0.76
    ropolitan
    -0.66
    alm
    -0.66
    RAFT
    -0.65
     directors
    -0.65
     carriers
    -0.62
    urger
    -0.62
    HAEL
    -0.62
    SHIP
    -0.61
     special
    -0.61
    POSITIVE LOGITS
    itary
    1.13
    Sol
    1.10
     Sol
    1.05
    ving
    0.98
    stice
    0.97
    ved
    0.95
    oshenko
    0.93
    vable
    0.90
    idon
    0.89
    ven
    0.86
    Activations Density 0.005%

    No Known Activations