Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 96
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance and observation

    oai_token-act-pair · gpt-3.5-turbo

    words related to surveillance and observation

    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
     Brill
    -0.73
     Wonderland
    -0.68
     Zionism
    -0.65
     Ples
    -0.65
    ãĤ¶
    -0.63
     Unch
    -0.62
     Gaul
    -0.61
     Bowser
    -0.58
     Creed
    -0.58
     chains
    -0.58
    POSITIVE LOGITS
    ê
    0.77
    pecting
    0.75
    fit
    0.74
    cliffe
    0.73
     COURT
    0.73
    Downloadha
    0.73
    imate
    0.70
    illance
    0.69
    perse
    0.68
    latable
    0.67
    Activations Density 0.106%

    No Known Activations