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. 10-RES-JB
    6. 22863
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive experiences or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or excitement about various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alties
    -0.80
    gans
    -0.78
    anwhile
    -0.76
    itored
    -0.73
    Ĭ±
    -0.72
    annels
    -0.70
    associated
    -0.70
    engers
    -0.70
    ilon
    -0.68
    Ĵ
    -0.66
    POSITIVE LOGITS
     crochet
    1.09
     recipe
    1.09
     tutorial
    1.07
     blog
    1.04
     gif
    1.03
     playthrough
    1.03
     manga
    1.00
     poem
    1.00
     infographic
    0.99
     article
    0.97
    Activations Density 0.471%

    No Known Activations