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. 6-RES-JB
    6. 19441
    Prev
    Next
    INDEX
    Explanations

    phrases indicating goals or aims

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating objectives or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appears
    -0.69
     Torn
    -0.69
    faces
    -0.66
    hot
    -0.64
    note
    -0.63
     declarations
    -0.63
    guards
    -0.63
     Used
    -0.63
     Kop
    -0.61
     Lemon
    -0.61
    POSITIVE LOGITS
     maximize
    1.14
     conserve
    1.06
     emulate
    1.06
     stimulate
    1.05
     minimize
    1.04
     preserve
    1.04
     promote
    1.04
     provide
    1.03
     achieve
    1.01
     eliminate
    1.01
    Activations Density 0.171%

    No Known Activations