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. 8-RES-JB
    6. 21400
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of presence or existence

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of presence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imb
    -0.83
    ousse
    -0.71
    ifiable
    -0.70
    cipled
    -0.70
    jug
    -0.69
     fixme
    -0.68
    bard
    -0.66
    raid
    -0.64
    mie
    -0.63
    itals
    -0.63
    POSITIVE LOGITS
    uated
    0.93
    enance
    0.88
     presence
    0.86
     quo
    0.75
    uate
    0.74
     Presence
    0.74
    iveness
    0.73
     abroad
    0.69
    uality
    0.66
     unseen
    0.65
    Activations Density 0.048%

    No Known Activations