© 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. 688
    Prev
    Next
    INDEX
    Explanations

    phrases related to law, investigations, and official events

    oai_token-act-pair · gpt-3.5-turbo

    elements related to conflict or disagreement

    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
     domest
    -0.51
    bred
    -0.47
    adena
    -0.43
     artisan
    -0.43
    animate
    -0.42
    packed
    -0.42
     miniature
    -0.41
     vegetarian
    -0.41
     Sty
    -0.41
    liter
    -0.41
    POSITIVE LOGITS
    ãģ®é
    0.55
     explan
    0.52
    ij士
    0.51
    upon
    0.51
     paraph
    0.51
     inconsistencies
    0.51
     implying
    0.50
     reiterate
    0.50
     inconsistency
    0.50
    Comment
    0.50
    Activations Density 2.029%

    No Known Activations