© 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. 3393
    Prev
    Next
    INDEX
    Explanations

    phrases related to offering assistance or guidance

    oai_token-act-pair · gpt-3.5-turbo

    phrases that imply assistance or help from a collective entity

    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
     quo
    -0.62
     totality
    -0.61
    SpaceEngineers
    -0.59
     Bundy
    -0.57
     unfocusedRange
    -0.57
    math
    -0.57
    Reply
    -0.56
     looms
    -0.56
    rising
    -0.56
    going
    -0.55
    POSITIVE LOGITS
    bsite
    1.13
    're
    1.12
     recommend
    1.05
     specialize
    1.02
    igh
    1.01
    arers
    1.01
    'll
    1.00
    've
    0.99
     strive
    0.96
    avers
    0.95
    Activations Density 0.134%

    No Known Activations