© 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
    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. 17150
    Prev
    Next
    INDEX
    Explanations

    mentions of "top" rankings or positions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating rankings or positions of importance

    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
    ufact
    -0.73
     Mub
    -0.67
    asca
    -0.66
    ajor
    -0.66
     Consent
    -0.65
    Äĩ
    -0.62
     consent
    -0.62
     Ana
    -0.62
     Gaul
    -0.62
    cci
    -0.61
    POSITIVE LOGITS
    most
    1.22
    ographical
    1.01
     tier
    0.98
     drawer
    0.94
    iary
    0.92
     scorer
    0.88
    ography
    0.87
    liest
    0.83
     notch
    0.82
    eka
    0.80
    Activations Density 0.032%

    No Known Activations