© 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. 14082
    Prev
    Next
    INDEX
    Explanations

    time-related expressions including phrases such as 'three-week', 'after', or 'years'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time duration or the completion of an action

    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
    HO
    -0.68
    chev
    -0.68
    posts
    -0.65
    interstitial
    -0.64
    ports
    -0.63
    ãĥ¯
    -0.63
    cause
    -0.62
     redistributed
    -0.61
    éĹĺ
    -0.60
    chuk
    -0.58
    POSITIVE LOGITS
     hiatus
    1.18
     lengthy
    1.16
     protracted
    1.15
     tumultuous
    1.09
     brief
    1.06
     prolonged
    1.05
     gru
    1.02
     unsuccessful
    1.00
     disastrous
    0.97
     successful
    0.96
    Activations Density 0.125%

    No Known Activations