© 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. 22229
    Prev
    Next
    INDEX
    Explanations

    verbs that denote assisting or providing support

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assistance or support

    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
    é¾
    -0.80
     Deer
    -0.67
    War
    -0.64
    Pict
    -0.64
    meat
    -0.63
    bish
    -0.62
    Bow
    -0.62
    gran
    -0.57
     cel
    -0.57
     Goth
    -0.57
    POSITIVE LOGITS
    fully
    1.01
     facilitate
    0.88
     alleviate
    0.75
     Desk
    0.75
    Desk
    0.73
    heet
    0.73
    aceous
    0.71
    meet
    0.70
    hift
    0.70
     relieve
    0.70
    Activations Density 0.043%

    No Known Activations