© 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 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. 0-RES-JB
    11. 12344
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of derivation or origin

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the origin or source of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lock
    -0.72
    ucket
    -0.72
    sil
    -0.68
    gers
    -0.68
     pace
    -0.67
    ress
    -0.65
    mess
    -0.65
    aggressive
    -0.64
    camp
    -0.63
     Quiet
    -0.63
    POSITIVE LOGITS
     derived
    3.40
     derive
    2.35
    derived
    2.29
     derives
    2.09
     deriv
    1.92
     inferred
    1.51
     extracted
    1.48
     derivative
    1.47
     obtained
    1.40
     computed
    1.38
    Activations Density 0.016%

    No Known Activations