© 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. 2-RES-JB
    11. 7606
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in '-ive' or '-ary' related to characteristics, actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the words "intensive" and "contrary" in various contexts

    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
    ittees
    -0.71
    imore
    -0.71
     dissatisfied
    -0.71
    cow
    -0.68
     upl
    -0.68
     behold
    -0.65
    âĻ¦
    -0.64
    isSpecialOrderable
    -0.64
     incumbent
    -0.64
    20439
    -0.63
    POSITIVE LOGITS
    enegger
    0.94
    rary
    0.87
    ly
    0.82
    anwhile
    0.78
    nesses
    0.76
    riel
    0.75
    olars
    0.72
    itals
    0.69
    sers
    0.69
    ensive
    0.69
    Activations Density 0.027%

    No Known Activations