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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1824
    Prev
    Next
    INDEX
    Explanations

    mentions of bodies of water, particularly oceans

    oai_token-act-pair · gpt-3.5-turbo

    references to oceanic environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.83
    TI
    -0.79
    POS
    -0.75
    nder
    -0.74
    TOP
    -0.69
    NER
    -0.69
    DIR
    -0.67
    mingham
    -0.66
    puff
    -0.65
    Filename
    -0.65
    POSITIVE LOGITS
    front
    1.09
    ographer
    1.03
     basin
    1.03
     liner
    0.97
     Ocean
    0.92
     ocean
    0.91
    ographers
    0.89
     circulation
    0.86
    ographic
    0.86
     waters
    0.85
    Activations Density 0.009%

    No Known Activations