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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 19100
    Prev
    Next
    INDEX
    Explanations

    personal statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "I am," indicating expressions of identity or state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entails
    -0.67
     Colleges
    -0.63
     Gap
    -0.63
     Which
    -0.62
    ainer
    -0.61
     externalToEVAOnly
    -0.61
     Lack
    -0.61
     payoff
    -0.59
     Ukrain
    -0.59
     hatch
    -0.58
    POSITIVE LOGITS
     thankful
    1.07
     glad
    1.04
    azon
    1.03
     grateful
    0.99
     honored
    0.96
     proud
    0.96
     hereby
    0.95
     honoured
    0.91
     fortunate
    0.89
     not
    0.85
    Activations Density 0.079%

    No Known Activations