© 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. 6-RES-JB
    11. 7574
    Prev
    Next
    INDEX
    Explanations

    sentences containing advice or warnings

    oai_token-act-pair · gpt-3.5-turbo

    empty or non-informative segments of text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.69
    Tokens
    -0.54
    vertisement
    -0.53
     disadvant
    -0.51
     Vaugh
    -0.50
    gerald
    -0.50
     seiz
    -0.50
     '[
    -0.49
    èĢħ
    -0.49
    Mobil
    -0.48
    POSITIVE LOGITS
     alot
    0.70
     english
    0.64
    !!!!
    0.60
     :)
    0.60
     HUGE
    0.58
     pics
    0.57
     kinda
    0.56
     awesome
    0.56
     amazing
    0.56
     VERY
    0.56
    Activations Density 1.208%

    No Known Activations