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. 7645
    Prev
    Next
    INDEX
    Explanations

    adjectives related to physical ability or disability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ability and disability

    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
     Canaver
    -0.73
    ocene
    -0.63
    uble
    -0.61
     Guinness
    -0.60
    Corp
    -0.60
    ppard
    -0.59
    earable
    -0.59
    arty
    -0.59
    urized
    -0.58
    ourke
    -0.58
    POSITIVE LOGITS
    ness
    0.83
     guiActiveUn
    0.75
    NESS
    0.72
     trades
    0.68
    nesses
    0.65
     citiz
    0.64
    iaries
    0.64
    iary
    0.59
     cred
    0.59
     themselves
    0.58
    Activations Density 0.259%

    No Known Activations