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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11098
    Prev
    Next
    INDEX
    Explanations

    words related to needs and requirements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to necessity and lack in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yssey
    -0.59
    DragonMagazine
    -0.58
    oche
    -0.58
    )</
    -0.58
    ãĥł
    -0.57
    abet
    -0.56
    )!
    -0.55
    atsuki
    -0.55
    )|
    -0.54
    ISE
    -0.53
    POSITIVE LOGITS
     anymore
    1.01
     but
    1.01
     whereas
    0.90
     or
    0.88
    but
    0.84
     nor
    0.81
     etc
    0.78
    yet
    0.77
     yet
    0.76
     rather
    0.76
    Activations Density 0.564%

    No Known Activations