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. 3-RES-JB
    6. 22175
    Prev
    Next
    INDEX
    Explanations

    phrases describing compositions or structures

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the composition or structure of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hawks
    -0.67
    ilings
    -0.67
    bury
    -0.65
    Flying
    -0.61
     Karma
    -0.60
    WT
    -0.60
     Taj
    -0.60
     Dull
    -0.58
    fly
    -0.58
    Sil
    -0.58
    POSITIVE LOGITS
     consist
    0.89
    galitarian
    0.87
    ģ«
    0.85
     consisted
    0.81
     comprised
    0.80
     solely
    0.79
     consists
    0.78
    encies
    0.78
    ĸļ
    0.76
    alion
    0.76
    Activations Density 0.010%

    No Known Activations