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. 9-RES-JB
    6. 16860
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences emphasizing the significance or impact of something

    oai_token-act-pair · gpt-3.5-turbo

    the presence of descriptions and attributes of small, fictional creatures or Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptives
    -0.78
    apons
    -0.76
    ©¶æ
    -0.76
    £ı
    -0.75
    manship
    -0.71
    brids
    -0.69
    llor
    -0.69
    Frames
    -0.67
    ivalry
    -0.67
    oust
    -0.67
    POSITIVE LOGITS
    gie
    1.30
     chunk
    1.07
     mistake
    1.00
    oted
    0.96
     deal
    0.95
     difference
    0.94
     misconception
    0.91
    gest
    0.91
     disappointment
    0.90
     understatement
    0.89
    Activations Density 0.083%

    No Known Activations