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. 3838
    Prev
    Next
    INDEX
    Explanations

    descriptions of impressive or extraordinary structures

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of significant architectural or artistic works

    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
    ividual
    -0.60
     helicop
    -0.58
    enhagen
    -0.57
     equivalents
    -0.55
    afety
    -0.55
     [*
    -0.52
    alion
    -0.52
     nomine
    -0.51
    abee
    -0.51
     elig
    -0.50
    POSITIVE LOGITS
     cinematic
    0.60
     sci
    0.54
     iconic
    0.53
     LGBTQ
    0.52
    \":
    0.51
     psychedelic
    0.51
     âĢº
    0.51
     scenery
    0.51
     cuisine
    0.50
     fandom
    0.49
    Activations Density 1.725%

    No Known Activations