© 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. 368
    Prev
    Next
    INDEX
    Explanations

    verbs that introduce reported speech or clarification, such as "stating" or "noting"

    oai_token-act-pair · gpt-4-turbo

    quotations or statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of stating or noting information

    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
    ombat
    -0.77
    efer
    -0.71
    nin
    -0.70
    ppa
    -0.66
    behind
    -0.66
    deal
    -0.66
    umm
    -0.65
    omet
    -0.64
    boot
    -0.62
    talk
    -0.61
    POSITIVE LOGITS
    redients
    0.83
    BuyableInstoreAndOnline
    0.81
    tons
    0.81
    bird
    0.68
    INTON
    0.64
     conduc
    0.64
    birds
    0.64
    LESS
    0.62
    wcsstore
    0.62
    ADRA
    0.60
    Activations Density 0.153%

    No Known Activations