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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24430
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or offering assistance

    oai_token-act-pair · gpt-3.5-turbo

    references to assistance or support

    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
    ross
    -0.78
    ategory
    -0.71
     Observatory
    -0.68
     Revel
    -0.67
     Blend
    -0.64
    Pict
    -0.63
     Collider
    -0.63
    ilib
    -0.62
     smoker
    -0.59
     Coil
    -0.59
    POSITIVE LOGITS
    des
    1.11
    fully
    1.10
    meet
    0.93
     locating
    0.87
     navigating
    0.83
    giving
    0.82
    ocating
    0.81
     urgently
    0.81
     Desk
    0.79
    ings
    0.79
    Activations Density 0.047%

    No Known Activations