© 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. 17234
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to tangible things or results

    oai_token-act-pair · gpt-3.5-turbo

    references to tangible items or results

    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
    ften
    -0.80
    ammers
    -0.79
    cker
    -0.75
    giene
    -0.73
    ©¶æ
    -0.73
    xual
    -0.73
    alian
    -0.71
     specialize
    -0.69
    unin
    -0.68
    enhagen
    -0.67
    POSITIVE LOGITS
     tangible
    0.93
    TY
    0.87
     manifestation
    0.80
    aneously
    0.79
    isable
    0.77
    çIJ
    0.76
     IMAGES
    0.75
    izable
    0.74
    atform
    0.74
    Effects
    0.73
    Activations Density 0.029%

    No Known Activations