© 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. 10-RES-JB
    11. 24297
    Prev
    Next
    INDEX
    Explanations

    phrases consisting of "in a" followed by an adjective and a noun

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe characteristics or qualities in a versatile context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATURES
    -0.75
    AUD
    -0.67
    reon
    -0.66
    aints
    -0.66
    allion
    -0.65
    Extra
    -0.64
     icons
    -0.63
     Influence
    -0.62
    oola
    -0.62
    associated
    -0.62
    POSITIVE LOGITS
     nutshell
    1.49
     hurry
    1.36
     manner
    1.18
     heartbeat
    1.14
     pinch
    1.09
     timely
    1.02
     vacuum
    0.99
     variety
    0.88
     way
    0.86
     phased
    0.85
    Activations Density 0.117%

    No Known Activations