© 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. 7442
    Prev
    Next
    INDEX
    Explanations

    verbs related to providing instructions or advice

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or tasks that need to be done

    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
    haw
    -0.75
     clans
    -0.72
     pursu
    -0.70
     carts
    -0.68
     crane
    -0.67
     races
    -0.67
     elders
    -0.66
     haul
    -0.66
    iture
    -0.66
     hatch
    -0.65
    POSITIVE LOGITS
    rael
    0.87
    KER
    0.82
    olation
    0.81
    ovie
    0.78
     NOT
    0.77
    nt
    0.77
     ALWAYS
    0.75
     Solitaire
    0.74
     simply
    0.73
    senal
    0.72
    Activations Density 0.205%

    No Known Activations