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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4575
    Prev
    Next
    INDEX
    Explanations

    references to the element "iron" and actions related to iron

    oai_token-act-pair · gpt-3.5-turbo

    references to iron, both as a material and in various contexts

    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
    olitan
    -0.73
    adows
    -0.72
    lus
    -0.72
     Garr
    -0.71
     Retrieved
    -0.70
    AUD
    -0.69
    itia
    -0.68
    anchester
    -0.68
    soType
    -0.67
    sound
    -0.66
    POSITIVE LOGITS
    clad
    1.33
     ore
    1.07
     oxide
    0.96
     iron
    0.88
    works
    0.88
    chest
    0.86
     skillet
    0.85
    worker
    0.81
     fist
    0.80
    worm
    0.80
    Activations Density 0.014%

    No Known Activations