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. 11934
    Prev
    Next
    INDEX
    Explanations

    phrases related to database management and software development

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to databases and user management within a programming context

    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
    ALLY
    -0.75
    away
    -0.72
    sw
    -0.72
    SHIP
    -0.69
    lier
    -0.69
    Pont
    -0.65
    bable
    -0.64
    liest
    -0.63
    rick
    -0.63
    RANT
    -0.63
    POSITIVE LOGITS
    paces
    1.32
    pace
    1.26
    ettings
    1.24
    ource
    1.22
    ystem
    1.21
    hip
    1.19
    cript
    1.15
    poons
    1.14
    ilver
    1.12
    hips
    1.11
    Activations Density 0.419%

    No Known Activations