© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    names of cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms, especially those related to organizations or locations

    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
    oute
    -0.77
    role
    -0.73
    VALUE
    -0.67
    agonists
    -0.65
    uster
    -0.63
     Clicker
    -0.60
    acter
    -0.60
    ceptor
    -0.59
    riet
    -0.59
    msg
    -0.58
    POSITIVE LOGITS
    ESE
    1.16
     Lumpur
    1.01
    ese
    0.96
     Airways
    0.94
    istan
    0.93
     natives
    0.92
     peninsula
    0.90
     Tourism
    0.89
     coast
    0.87
     Province
    0.86
    Activations Density 0.396%

    No Known Activations