© 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. 10-RES-JB
    11. 13556
    Prev
    Next
    INDEX
    Explanations

    terms related to speed and rate of change

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with speed and acceleration in various contexts

    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
    owship
    -0.71
    bors
    -0.70
    »Ĵ
    -0.68
    nil
    -0.67
    #$#$
    -0.66
     Marketable
    -0.65
    ukong
    -0.65
    rums
    -0.64
    gdala
    -0.64
    Champ
    -0.63
    POSITIVE LOGITS
     pace
    1.37
     progress
    1.24
     turnaround
    1.19
     uptake
    1.18
     progression
    1.10
     recovery
    1.08
     deterioration
    1.08
     onset
    1.07
     rollout
    1.06
     development
    1.06
    Activations Density 0.161%

    No Known Activations