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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 22995
    Prev
    Next
    INDEX
    Explanations

    words related to metal

    oai_token-act-pair · gpt-3.5-turbo

    references to metal objects or materials

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

    No Comments

    Negative Logits
     Polk
    -0.76
    olitan
    -0.70
    HCR
    -0.70
    rolet
    -0.67
    zee
    -0.67
    ========
    -0.67
     Summers
    -0.65
     Katrina
    -0.65
    assies
    -0.64
     Nurs
    -0.64
    POSITIVE LOGITS
    anguage
    1.61
     detectors
    1.28
     oxide
    1.21
     detector
    1.10
    works
    1.05
    bending
    0.96
    weights
    0.95
    mith
    0.91
     metal
    0.90
    workers
    0.90
    Activations Density 0.012%

    No Known Activations