© 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. 4-RES-JB
    11. 14891
    Prev
    Next
    INDEX
    Explanations

    words related to fast or quick actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to efficiency and expedited processes

    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
    Interstitial
    -0.80
    pour
    -0.73
    Fram
    -0.67
    corn
    -0.66
    enegger
    -0.65
    REL
    -0.65
     Soda
    -0.64
    bane
    -0.64
    maker
    -0.64
    Maker
    -0.64
    POSITIVE LOGITS
     exped
    1.21
    iency
    1.15
    itions
    1.09
    ited
    1.06
    iencies
    1.01
    itious
    1.00
    ient
    0.98
    iences
    0.95
    ience
    0.95
    anced
    0.95
    Activations Density 0.007%

    No Known Activations