© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3268
    Prev
    Next
    INDEX
    Explanations

    phrases related to tampering or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tampering" and related forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĺħ
    -0.77
    falls
    -0.73
    hens
    -0.70
     Primal
    -0.70
    RG
    -0.66
    sson
    -0.64
    ppo
    -0.63
    pu
    -0.63
     Adren
    -0.61
    Route
    -0.60
    POSITIVE LOGITS
     tampering
    1.21
     tink
    1.03
     tam
    0.95
    iddled
    0.88
    aven
    0.74
    inker
    0.73
    redd
    0.70
    ritten
    0.70
    ocalypse
    0.69
    arks
    0.69
    Activations Density 0.020%

    No Known Activations