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. 12-RES-JB
    6. 15089
    Prev
    Next
    INDEX
    Explanations

    sentences with numbers or abbreviations followed by period and one-syllable common verbs like 'say', 'reduce', and 'vote'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    specific numeric values and their contextual relevance in various narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ò
    -1.29
    Þ
    -1.25
    ö
    -1.20
    ě
    -1.20
    Ý
    -1.20
    À
    -1.19
    ÿ
    -1.19
    Ă
    -1.19
    	
    -1.19
    rawdownload
    -1.19
    POSITIVE LOGITS
    won
    0.44
    't
    0.44
    hide
    0.42
    ca
    0.42
    ge
    0.42
    v
    0.42
    bm
    0.42
    gov
    0.41
    wed
    0.41
    wide
    0.41
    Activations Density 1.249%

    No Known Activations