© 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. 9-RES-JB
    11. 2814
    Prev
    Next
    INDEX
    Explanations

    phrases related to beginning or initiating an action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "enter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attribute
    -0.63
    _-
    -0.61
    esa
    -0.60
    gnu
    -0.60
    ankind
    -0.59
    MpServer
    -0.59
    plement
    -0.58
    obe
    -0.58
    iggs
    -0.58
    cussion
    -0.58
    POSITIVE LOGITS
    prising
    1.39
    tain
    1.09
    prises
    1.09
    prise
    1.04
     into
    1.03
     INTO
    0.94
    TAIN
    0.93
    tained
    0.92
    tainment
    0.88
    taining
    0.85
    Activations Density 0.038%

    No Known Activations