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. 4805
    Prev
    Next
    INDEX
    Explanations

    words related to computer programming, security, and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coding or programming languages

    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
     Arabian
    -0.67
     Borders
    -0.65
     Dos
    -0.65
     Sea
    -0.64
     Mek
    -0.64
     Richards
    -0.63
     Nicarag
    -0.63
     lull
    -0.63
     Norris
    -0.63
     Ell
    -0.62
    POSITIVE LOGITS
    based
    1.35
    specific
    1.21
    sized
    1.20
    derived
    1.17
    level
    1.16
    related
    1.15
    type
    1.13
    driven
    1.13
    centric
    1.13
    wise
    1.12
    Activations Density 0.138%

    No Known Activations