© 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. 706
    Prev
    Next
    INDEX
    Explanations

    phrases related to consistent or routine actions

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of actions or events occurring on a regular basis

    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
     Geh
    -0.70
     Mara
    -0.69
     Warden
    -0.69
     Millennium
    -0.68
    holes
    -0.67
     Warriors
    -0.67
    elo
    -0.67
     Lore
    -0.67
    lad
    -0.66
     Way
    -0.65
    POSITIVE LOGITS
     spaced
    1.05
    theless
    0.91
     encountered
    0.86
     monitored
    0.85
     pract
    0.84
     consulted
    0.84
    entimes
    0.84
     encount
    0.83
     Asked
    0.82
     employed
    0.81
    Activations Density 0.017%

    No Known Activations