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. 7-RES-JB
    6. 21854
    Prev
    Next
    INDEX
    Explanations

    minerals or materials used in construction and everyday objects

    oai_token-act-pair · gpt-3.5-turbo

    references to various materials, particularly metals and stones, used in construction or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kids
    -0.82
    onym
    -0.81
    angered
    -0.77
    Leary
    -0.77
    arenthood
    -0.76
    danger
    -0.76
    hoff
    -0.76
    OPA
    -0.76
    manac
    -0.76
    hey
    -0.75
    POSITIVE LOGITS
     oxide
    1.10
     coffin
    1.08
     alloy
    1.07
     accents
    1.03
     exterior
    0.99
     dioxide
    0.99
     fabrication
    0.98
     casing
    0.96
     clad
    0.96
     tubing
    0.95
    Activations Density 0.146%

    No Known Activations