© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 2637
    Prev
    Next
    INDEX
    Explanations

    words or phrases ending in 'ef'

    oai_token-act-pair · gpt-3.5-turbo

    mentions related to a specific organization or its activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Passenger
    -0.66
     Galactic
    -0.63
    =-=-=-=-
    -0.63
     ply
    -0.62
    )=(
    -0.62
    âĸ¬
    -0.61
    kees
    -0.61
    âĶģ
    -0.60
     denying
    -0.58
     bear
    -0.57
    POSITIVE LOGITS
    inition
    1.26
    icient
    1.25
    riend
    1.13
    onso
    1.12
    orce
    1.09
    initely
    1.09
    ornia
    1.07
    amily
    1.02
    iciency
    1.01
    rost
    1.01
    Activations Density 0.011%

    No Known Activations