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. 3-RES-JB
    6. 21723
    Prev
    Next
    INDEX
    Explanations

    adjectives related to the physical condition of being worn or aging

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'worn' used in various contexts

    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
    aminer
    -0.96
    reme
    -0.84
     Chomsky
    -0.74
    xual
    -0.73
    izoph
    -0.68
    ommod
    -0.68
    ISO
    -0.68
    ylum
    -0.67
    gdala
    -0.67
    liga
    -0.66
    POSITIVE LOGITS
     worn
    1.25
    nesday
    0.96
     captcha
    0.94
    worn
    0.89
     sleeves
    0.87
    adoes
    0.83
     fashioned
    0.76
     clothing
    0.76
     straps
    0.75
     wrist
    0.75
    Activations Density 0.008%

    No Known Activations