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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    6. 14811
    Prev
    Next
    INDEX
    Explanations

    references to a specific concept or object that is necessary or essential for a certain action or condition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "an."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BLE
    -0.77
    stones
    -0.66
     scares
    -0.66
    hood
    -0.66
     psychiat
    -0.65
     pupils
    -0.65
    Things
    -0.64
    cules
    -0.64
    âĸº
    -0.63
     Continued
    -0.62
    POSITIVE LOGITS
    abolic
    1.18
    agram
    1.04
    onym
    1.04
    cients
    1.03
    esthetic
    1.00
    omal
    0.97
    alogue
    0.96
    aer
    0.96
    ointed
    0.95
    ormal
    0.91
    Activations Density 0.267%

    No Known Activations