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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 22339
    Prev
    Next
    INDEX
    Explanations

    words related to acts of chopping or cutting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ch" within various contexts, indicating a focus on words that contain this specific character sequence

    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
    PORT
    -0.83
    gaard
    -0.76
    WARD
    -0.75
    ITED
    -0.74
    INGTON
    -0.74
    ENCE
    -0.73
    DragonMagazine
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
    berman
    -0.69
    glas
    -0.67
    POSITIVE LOGITS
    amps
    1.33
    icago
    1.13
    inese
    1.09
    ipper
    1.07
    ipping
    1.06
    aps
    1.05
    amp
    1.05
    ippers
    1.05
    akra
    1.04
    ipped
    1.04
    Activations Density 0.016%

    No Known Activations