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. 3014
    Prev
    Next
    INDEX
    Explanations

    references to different types of birds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of birds

    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
     Mods
    -0.77
     Stim
    -0.70
     DPR
    -0.70
    \\\\\\\\
    -0.67
    âĨij
    -0.67
    itate
    -0.66
     McMahon
    -0.66
     Reilly
    -0.65
     Levy
    -0.65
    anooga
    -0.65
    POSITIVE LOGITS
     bird
    3.60
     birds
    2.58
    Bird
    2.47
     Bird
    2.39
    bird
    2.23
     Birds
    2.12
     owl
    1.84
    birds
    1.83
     pigeon
    1.76
     eagle
    1.75
    Activations Density 0.019%

    No Known Activations