© 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. 7-RES-JB
    11. 19006
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating movement or change

    oai_token-act-pair · gpt-3.5-turbo

    verbs and actions related to dynamics and changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.78
    ILLE
    -0.65
    inately
    -0.64
    eers
    -0.64
     charism
    -0.60
    SOURCE
    -0.60
    agall
    -0.59
    ishly
    -0.58
    atalie
    -0.57
    ALLY
    -0.57
    POSITIVE LOGITS
    creen
    1.42
    pace
    1.42
    hift
    1.38
    paces
    1.30
    peed
    1.25
    heet
    1.23
    ettings
    1.14
    pring
    1.11
    mith
    1.11
    hops
    1.09
    Activations Density 0.390%

    No Known Activations