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. 6-RES-JB
    6. 1266
    Prev
    Next
    INDEX
    Explanations

    words related to excessive or extreme situations or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the term "overly" and its variations, indicating extreme qualities or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ians
    -0.81
    ector
    -0.80
    arium
    -0.78
    ician
    -0.76
    igi
    -0.75
    zon
    -0.73
    iens
    -0.73
    ochet
    -0.73
    itudinal
    -0.72
    ilet
    -0.71
    POSITIVE LOGITS
     simplistic
    0.79
     burdens
    0.79
    ealous
    0.75
     indul
    0.74
     inflated
    0.73
     aggressive
    0.73
     capacitor
    0.72
     adolesc
    0.72
     excessive
    0.71
     partying
    0.70
    Activations Density 0.034%

    No Known Activations