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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 8
    Prev
    Next
    INDEX
    Explanations

    words related to landscaping and shaping

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and past participles related to the concept of shaping in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perman
    -0.60
     Brah
    -0.60
     Historical
    -0.60
     JR
    -0.58
     irre
    -0.57
     Stat
    -0.57
    JS
    -0.57
     stal
    -0.57
     rot
    -0.57
     Joh
    -0.56
    POSITIVE LOGITS
    aping
    4.27
    aped
    3.75
    apes
    2.83
    ape
    2.17
    apers
    2.09
    APE
    2.03
    aper
    1.80
    aps
    1.70
    aving
    1.18
    ap
    1.16
    Activations Density 0.013%

    No Known Activations