© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 18380
    Prev
    Next
    INDEX
    Explanations

    phrases related to formal statements or declarations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a."

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

    No Comments

    Negative Logits
    plates
    -0.74
    cair
    -0.70
     ducks
    -0.70
    tics
    -0.67
    ogi
    -0.67
    wagon
    -0.67
    effects
    -0.66
    onut
    -0.64
     enjoys
    -0.64
     clones
    -0.64
    POSITIVE LOGITS
     briefing
    0.97
     statement
    0.92
     keynote
    0.87
     lengthy
    0.86
     meeting
    0.86
     conference
    0.84
     brief
    0.80
     flurry
    0.80
     bid
    0.79
     scathing
    0.79
    Activations Density 0.238%

    No Known Activations