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. 22750
    Prev
    Next
    INDEX
    Explanations

    words related to steel or things associated with the term "steel."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Steel" and related terms

    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
    monary
    -0.88
    istries
    -0.86
    ged
    -0.84
    omez
    -0.80
    anchester
    -0.77
    gments
    -0.77
    gencies
    -0.75
    ging
    -0.74
    umen
    -0.73
    perature
    -0.73
    POSITIVE LOGITS
     Crate
    0.93
    Series
    0.82
     Vaugh
    0.70
    ombat
    0.70
     Steelers
    0.69
     âĶľ
    0.67
    ORED
    0.67
     Peb
    0.67
    theme
    0.65
    atted
    0.64
    Activations Density 0.038%

    No Known Activations