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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 23513
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific acronym (KE) followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "KE" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ional
    -0.73
    actionDate
    -0.71
    inant
    -0.65
     tremend
    -0.65
    inatory
    -0.63
    ãĤ¨ãĥ«
    -0.63
    acity
    -0.63
     thous
    -0.62
    itivity
    -0.61
     circ
    -0.59
    POSITIVE LOGITS
    KE
    1.25
    VO
    1.04
    IRO
    1.02
    YS
    0.98
    LEY
    0.98
    LAND
    0.87
    VID
    0.87
    VICE
    0.86
    Maker
    0.83
    AMY
    0.83
    Activations Density 0.007%

    No Known Activations