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. 10-RES-JB
    6. 11718
    Prev
    Next
    INDEX
    Explanations

    specific references to objects, places, or terms related to the word "eagle."

    oai_token-act-pair · gpt-3.5-turbo

    references to eagles or related bird terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERN
    -0.80
    eric
    -0.79
    acters
    -0.76
    orie
    -0.71
     Machina
    -0.69
    Wr
    -0.69
    ello
    -0.69
    AMI
    -0.68
    Contents
    -0.68
    ester
    -0.67
    POSITIVE LOGITS
     Feather
    0.86
    horn
    0.86
    agles
    0.85
     Scout
    0.85
    agle
    0.81
    hawk
    0.79
     eagle
    0.76
     flown
    0.75
     Claw
    0.75
     Eagle
    0.75
    Activations Density 0.040%

    No Known Activations