© 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. 7-RES-JB
    11. 2974
    Prev
    Next
    INDEX
    Explanations

    references to actions or events taking place

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation and sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gorge
    -0.67
     abduct
    -0.65
     murder
    -0.65
     inner
    -0.64
     compartment
    -0.63
     mur
    -0.63
     assassin
    -0.62
     minion
    -0.62
     hunger
    -0.61
     tyrann
    -0.61
    POSITIVE LOGITS
     Nonetheless
    1.18
     Nevertheless
    1.16
     Additionally
    1.11
     Though
    1.11
     Notably
    1.09
     However
    1.09
     Regardless
    1.08
     Ultimately
    1.08
     Eventually
    1.04
     Moreover
    1.03
    Activations Density 0.694%

    No Known Activations