© 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. 7-RES-JB
    11. 3208
    Prev
    Next
    INDEX
    Explanations

    technical terms related to information security and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to technology and security features

    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
    ilaterally
    -0.76
    stasy
    -0.73
    DonaldTrump
    -0.72
    abwe
    -0.70
    perty
    -0.67
     è£ıç
    -0.67
    amia
    -0.67
    chwitz
    -0.66
    actly
    -0.64
    î
    -0.63
    POSITIVE LOGITS
     consists
    0.82
     portion
    0.80
     however
    0.78
     consisted
    0.75
     retains
    0.73
     analogy
    0.72
     includes
    0.71
     therefore
    0.70
     assures
    0.68
     version
    0.68
    Activations Density 0.669%

    No Known Activations