© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 12163
    Prev
    Next
    INDEX
    Explanations

    words related to knowledge, awareness, and understanding

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating knowledge or understanding

    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
    MET
    -0.63
     Arms
    -0.63
    hell
    -0.62
    heit
    -0.62
     Railroad
    -0.59
    Unix
    -0.59
    icho
    -0.57
     lid
    -0.57
     Barrier
    -0.57
    ospace
    -0.57
    POSITIVE LOGITS
    dden
    0.70
    »Ĵ
    0.70
    figure
    0.69
    urger
    0.65
     unseen
    0.65
     forgive
    0.65
    rogen
    0.64
    soType
    0.63
     Testament
    0.61
     understand
    0.60
    Activations Density 0.177%

    No Known Activations