© 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. 17302
    Prev
    Next
    INDEX
    Explanations

    instances of the term "spam" in relation to unwanted or irrelevant content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to fraudulent activities

    oai_token-act-pair · gpt-3.5-turbo
    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
    ONSORED
    -0.67
     kinderg
    -0.66
    WIND
    -0.66
     anticipation
    -0.61
    yi
    -0.61
     tremend
    -0.61
     spirits
    -0.61
     unders
    -0.59
    REDACTED
    -0.58
     cooled
    -0.58
    POSITIVE LOGITS
    pling
    1.16
    nesty
    1.11
    ilies
    1.04
    sterdam
    1.03
    elia
    1.01
    pering
    1.01
    ilial
    1.00
    ilar
    0.99
    amia
    0.97
    essage
    0.95
    Activations Density 0.021%

    No Known Activations