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. 8-RES-JB
    6. 9142
    Prev
    Next
    INDEX
    Explanations

    references to various activities related to fishing

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to fishing

    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
    xual
    -0.89
    xus
    -0.76
    eus
    -0.74
    haar
    -0.74
    mble
    -0.69
    gow
    -0.68
    agonists
    -0.66
    heimer
    -0.65
    hesis
    -0.64
    XM
    -0.63
    POSITIVE LOGITS
     fisherman
    1.15
     fishing
    1.06
     fishermen
    1.02
     boats
    0.91
    fish
    0.88
     fisheries
    0.84
     fisher
    0.83
    bowl
    0.83
     boat
    0.82
    boat
    0.82
    Activations Density 0.034%

    No Known Activations