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. 6223
    Prev
    Next
    INDEX
    Explanations

    words related to cylinders and combustion in engines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to engines and mechanical components

    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
    won
    -0.77
    anamo
    -0.74
    ipeg
    -0.73
    escription
    -0.70
    egal
    -0.70
    stra
    -0.69
    uary
    -0.68
    asel
    -0.68
    emouth
    -0.68
    omen
    -0.68
    POSITIVE LOGITS
     cylinders
    1.02
     cylinder
    0.99
    wheel
    0.91
     combustion
    0.84
    oidal
    0.82
     piston
    0.80
     refill
    0.76
     Cumm
    0.73
    ttle
    0.71
    stall
    0.69
    Activations Density 0.026%

    No Known Activations