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. 0-RES-JB
    6. 19799
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of replicability or inexplicability

    oai_token-act-pair · gpt-3.5-turbo

    words related to applicability and relevance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dare
    -0.68
     traps
    -0.68
     privilege
    -0.67
     vigilance
    -0.66
    trap
    -0.64
    EMOTE
    -0.63
     rapists
    -0.62
     Guards
    -0.62
     patriotism
    -0.61
     prog
    -0.61
    POSITIVE LOGITS
    icable
    3.95
    icably
    3.74
    essel
    1.77
    [/
    1.23
    enz
    1.11
    istar
    0.96
     noticeable
    0.86
    ilde
    0.84
    icative
    0.80
     Flames
    0.76
    Activations Density 0.028%

    No Known Activations