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. 7-RES-JB
    6. 6010
    Prev
    Next
    INDEX
    Explanations

    words related to strong agreement or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the term "definitely" and its variations to express certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roups
    -0.87
    ently
    -0.86
    sembly
    -0.84
    acity
    -0.78
    lings
    -0.74
    aciously
    -0.73
    ously
    -0.71
    mits
    -0.70
     Mour
    -0.70
    lete
    -0.69
    POSITIVE LOGITS
     underest
    0.71
     Vader
    0.70
     recommend
    0.69
     impacted
    0.68
     correlated
    0.66
    ove
    0.65
     influenced
    0.64
     qualifies
    0.64
     bothered
    0.63
     differentiated
    0.63
    Activations Density 0.030%

    No Known Activations