© 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. 4-RES-JB
    11. 588
    Prev
    Next
    INDEX
    Explanations

    images or references related to turtles

    oai_token-act-pair · gpt-3.5-turbo

    references to turtles and related reptiles

    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
    Interstitial
    -0.93
    ãĥ¼ãĥĨ
    -0.78
    orship
    -0.72
     confir
    -0.68
    )=(
    -0.67
    iences
    -0.66
    sts
    -0.65
    used
    -0.65
    Null
    -0.64
    Ľ
    -0.64
    POSITIVE LOGITS
     turtle
    1.23
     turtles
    1.16
    fish
    1.11
    brates
    1.07
    brate
    1.04
     Turtle
    1.03
     Turtles
    0.96
    face
    0.83
    oche
    0.83
    Snake
    0.82
    Activations Density 0.017%

    No Known Activations