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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 11005
    Prev
    Next
    INDEX
    Explanations

    phrases related to asserting ownership or rights over something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "claim" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arrang
    -0.83
     Watching
    -0.75
     electing
    -0.70
     simul
    -0.69
     srf
    -0.68
     destro
    -0.68
     bom
    -0.68
     captcha
    -0.68
    ombo
    -0.67
     newcom
    -0.67
    POSITIVE LOGITS
    Claim
    0.86
     claims
    0.82
    oux
    0.80
    ulent
    0.77
    ifications
    0.76
    ylum
    0.76
     claim
    0.74
    uca
    0.74
    orial
    0.73
    aires
    0.73
    Activations Density 0.028%

    No Known Activations