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. 10-RES-JB
    6. 9383
    Prev
    Next
    INDEX
    Explanations

    references to things being certain or assured

    oai_token-act-pair · gpt-3.5-turbo

    the word "guaranteed" and its variations, indicating certainty or assurance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.93
    NetMessage
    -0.89
    insula
    -0.84
    annis
    -0.80
    ahime
    -0.73
    zanne
    -0.71
    ells
    -0.71
    kens
    -0.70
    anooga
    -0.69
    otom
    -0.69
    POSITIVE LOGITS
     authenticity
    0.96
     validity
    0.88
     guarantee
    0.87
     confidentiality
    0.86
     virginity
    0.86
     fulfillment
    0.83
     anonymity
    0.83
     shorth
    0.79
    worthiness
    0.78
     guarantees
    0.77
    Activations Density 0.051%

    No Known Activations