© 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. 12397
    Prev
    Next
    INDEX
    Explanations

    phrases related to enabling or allowing actions or capabilities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "to" indicating functions or capabilities

    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
     Explan
    -0.68
    laughter
    -0.67
    soDeliveryDate
    -0.66
     Brach
    -0.65
    lights
    -0.65
    stars
    -0.65
    Got
    -0.63
    Appearances
    -0.61
    Org
    -0.61
    á½
    -0.61
    POSITIVE LOGITS
     concentrate
    1.20
     easily
    1.18
     seamlessly
    1.15
     customize
    1.15
     differentiate
    1.13
     effortlessly
    1.12
     confidently
    1.10
     visualize
    1.09
     avoid
    1.08
     isolate
    1.07
    Activations Density 0.168%

    No Known Activations