© 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. 3-RES-JB
    11. 477
    Prev
    Next
    INDEX
    Explanations

    imperative verbs, especially related to actions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    imperative verbs and phrases that prompt action or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edge
    -0.74
    vae
    -0.72
    iege
    -0.68
    avior
    -0.65
    ROR
    -0.60
    GMT
    -0.60
    dom
    -0.60
    ammy
    -0.60
    ALE
    -0.59
    chief
    -0.59
    POSITIVE LOGITS
    able
    0.88
    ings
    0.88
    ardless
    0.76
    ably
    0.73
    ables
    0.72
    ers
    0.66
    ingly
    0.66
    holders
    0.66
    ership
    0.65
    ability
    0.64
    Activations Density 0.457%

    No Known Activations