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

    Neuronpedia

    Jacobian LensNEW
    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. 22521
    Prev
    Next
    INDEX
    Explanations

    words related to elongation or extension

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lengthening or prolonging a concept or action

    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
    iance
    -0.75
    ELF
    -0.74
    iquette
    -0.73
    ãĥīãĥ©
    -0.69
     Doctrine
    -0.68
    opoulos
    -0.67
    DragonMagazine
    -0.67
    Ops
    -0.66
    olicited
    -0.64
    Availability
    -0.64
    POSITIVE LOGITS
    thens
    1.37
    thening
    1.20
     leng
    1.14
     prolong
    1.06
     shorten
    0.86
     adjourn
    0.86
    umbers
    0.84
    slow
    0.84
    then
    0.81
    umber
    0.80
    Activations Density 0.017%

    No Known Activations