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. 11937
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations and names, particularly focusing on locations like Gatineau and specific people's names like Shalomit

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical names and notable individuals associated with them

    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
     arsen
    -0.74
    ¥ŀ
    -0.69
    interstitial
    -0.69
     coded
    -0.69
     confir
    -0.66
    intendent
    -0.66
    xual
    -0.65
     spaced
    -0.64
    colour
    -0.64
    imately
    -0.63
    POSITIVE LOGITS
    ez
    0.94
    ena
    0.87
    ahoo
    0.87
     Juliet
    0.85
    rice
    0.85
    ts
    0.85
    ienne
    0.84
    iera
    0.84
    oad
    0.78
    tto
    0.77
    Activations Density 0.020%

    No Known Activations