© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 14568
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    forms of expression or completion of actions

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

    No Comments

    Negative Logits
     trailing
    -0.68
     flock
    -0.63
     clipboard
    -0.60
     bush
    -0.60
     curfew
    -0.59
     Bounty
    -0.57
     holders
    -0.57
     gotta
    -0.56
     Suffolk
    -0.55
     Fuj
    -0.54
    POSITIVE LOGITS
     offline
    0.82
    quished
    0.80
     Tradable
    0.78
     anytime
    0.78
     cheaply
    0.77
    ades
    0.76
     easily
    0.76
    iotic
    0.73
     safely
    0.73
    ocene
    0.71
    Activations Density 0.125%

    No Known Activations