© 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. 1645
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a generalized concept or unspecified thing

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "anything" or unspecified subjects

    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
    fer
    -0.72
    irth
    -0.70
     anonymity
    -0.67
    ardi
    -0.67
    arb
    -0.66
    nec
    -0.65
    asio
    -0.64
    ritz
    -0.63
     Encyclopedia
    -0.63
    ulators
    -0.62
    POSITIVE LOGITS
     else
    1.69
    Else
    1.35
     resembling
    1.26
     Else
    1.10
    else
    0.97
    THING
    0.94
     remotely
    0.94
     imaginable
    0.93
     whatsoever
    0.88
     happens
    0.85
    Activations Density 0.046%

    No Known Activations