© 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. 22281
    Prev
    Next
    INDEX
    Explanations

    names of locations

    oai_token-act-pair · gpt-3.5-turbo

    important geographic locations or terms associated with them

    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
    ],"
    -0.54
    PsyNetMessage
    -0.53
    ungle
    -0.53
    DCS
    -0.52
     captcha
    -0.51
    idden
    -0.51
    abetes
    -0.51
    taboola
    -0.51
    )",
    -0.49
    dden
    -0.49
    POSITIVE LOGITS
     however
    0.82
     meanwhile
    0.79
     ---------
    0.72
     therefore
    0.68
    ogether
    0.64
     furthermore
    0.60
     moreover
    0.59
     though
    0.56
     declined
    0.55
     accordingly
    0.53
    Activations Density 2.043%

    No Known Activations