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. 2097
    Prev
    Next
    INDEX
    Explanations

    mentions of seafood, particularly salmon

    oai_token-act-pair · gpt-3.5-turbo

    references to salmon and other types of fish

    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
    ELD
    -0.77
    SPONSORED
    -0.71
    =-=-=-=-
    -0.69
    Eng
    -0.66
    activated
    -0.65
    NEY
    -0.63
    EAR
    -0.62
     [*
    -0.61
    units
    -0.61
    Known
    -0.60
    POSITIVE LOGITS
     salmon
    1.22
     trout
    1.10
    bowl
    0.86
    icum
    0.85
    fish
    0.84
    ibaba
    0.83
    weed
    0.81
     mosqu
    0.80
     Salmon
    0.80
     fishing
    0.79
    Activations Density 0.010%

    No Known Activations