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

    Neuronpedia

    Jacobian LensNEW
    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. 6993
    Prev
    Next
    INDEX
    Explanations

    words related to physical appearance and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in varied contexts

    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
    ¬¼
    -0.50
    iple
    -0.46
    izon
    -0.44
    odes
    -0.42
    ety
    -0.42
    orn
    -0.39
    ahu
    -0.38
    ocl
    -0.38
    rou
    -0.37
    cel
    -0.37
    POSITIVE LOGITS
     albeit
    0.86
     namely
    0.81
     although
    0.75
     respectively
    0.74
     etc
    0.70
     however
    0.68
     though
    0.68
     whereas
    0.67
     including
    0.64
     aka
    0.62
    Activations Density 1.174%

    No Known Activations