© 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. 5986
    Prev
    Next
    INDEX
    Explanations

    phrases related to persons or entities named "Con" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific company or organization

    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
    uyomi
    -0.75
    assetsadobe
    -0.70
    TPS
    -0.70
    terday
    -0.69
    ħĭ
    -0.66
    HAEL
    -0.62
    aceutical
    -0.62
    ĪĴ
    -0.61
    cffffcc
    -0.61
     nerv
    -0.61
    POSITIVE LOGITS
    ventions
    1.10
    nex
    1.10
    venient
    1.09
    crete
    1.08
    ceived
    1.03
    clusions
    1.02
    secut
    1.02
    ventional
    1.00
    yers
    0.96
    cession
    0.94
    Activations Density 0.006%

    No Known Activations