© 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. 17289
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Happened" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "happen" and related terms, as well as concepts of threats and their implications

    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
    20439
    -1.04
    Downloadha
    -0.78
    BuyableInstoreAndOnline
    -0.70
    HCR
    -0.68
    ctica
    -0.68
    ETHOD
    -0.67
    IVER
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.64
     captcha
    -0.63
     Coul
    -0.62
    POSITIVE LOGITS
    ened
    1.85
    ening
    1.69
    eners
    1.40
    ener
    1.30
    ens
    1.19
    en
    1.11
    nesses
    1.01
    eled
    0.99
    resa
    0.98
    roxy
    0.93
    Activations Density 0.030%

    No Known Activations