Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16204
    Prev
    Next
    INDEX
    Explanations

    instances of advice or instruction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social behavior and responsibility

    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
    >>>>>>>>
    -0.56
     Pwr
    -0.54
    ----------------------------------------------------------------
    -0.52
    nsic
    -0.52
    voy
    -0.51
     å¤
    -0.50
     Medline
    -0.50
    ================================
    -0.49
    =-=-
    -0.49
     Yon
    -0.48
    POSITIVE LOGITS
     interacted
    0.63
     desired
    0.63
     deems
    0.59
     metic
    0.59
    heit
    0.59
     deem
    0.57
     interact
    0.57
    ufact
    0.55
     actually
    0.55
     transitioned
    0.55
    Activations Density 0.799%

    No Known Activations