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. 8489
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries or conditions affecting the body

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word 'athlete.'

    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
     compressor
    -0.72
     artificially
    -0.72
     Gemini
    -0.71
     modulation
    -0.70
     compress
    -0.67
     imitation
    -0.64
     weeds
    -0.63
     Russia
    -0.63
     Buk
    -0.63
     Dispatch
    -0.62
    POSITIVE LOGITS
    ath
    4.55
    aths
    3.02
    ATH
    2.49
    athe
    1.98
    athy
    1.94
    athi
    1.84
    atha
    1.80
    athing
    1.74
    athan
    1.67
    athed
    1.62
    Activations Density 0.010%

    No Known Activations