© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3509
    Prev
    Next
    INDEX
    Explanations

    words related to tools, specifically hammers

    oai_token-act-pair · gpt-3.5-turbo

    references to hammers and hammering actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VICE
    -0.75
    apes
    -0.71
    Leary
    -0.71
    ected
    -0.66
    Wide
    -0.66
    Sav
    -0.66
     Relations
    -0.64
    resp
    -0.64
    ITIES
    -0.64
    Es
    -0.64
    POSITIVE LOGITS
     hammer
    1.36
     hammered
    1.03
    sonian
    1.00
    bats
    0.96
    hammer
    0.93
     hamm
    0.93
    matical
    0.91
     nails
    0.85
     axe
    0.82
     wrench
    0.78
    Activations Density 0.008%

    No Known Activations