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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 2805
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and body parts, specifically around the male reproductive system

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix "icle" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.77
    ublic
    -0.77
    itches
    -0.77
    retched
    -0.77
    itude
    -0.73
    itcher
    -0.72
    gotten
    -0.71
    band
    -0.69
    kins
    -0.69
    eways
    -0.67
    POSITIVE LOGITS
    icle
    1.31
    icles
    1.23
     Awakens
    0.78
    moon
    0.76
    llor
    0.72
    pool
    0.72
    buster
    0.69
     ejac
    0.69
    ious
    0.67
    glass
    0.67
    Activations Density 0.016%

    No Known Activations