© 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. 17465
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or emphasize points in a sentence, such as "see" or "look"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive sentence structures or phrases that emphasize the act of seeing or observing

    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
    è¦ļéĨĴ
    -0.72
    DN
    -0.70
     UNCLASSIFIED
    -0.65
     flu
    -0.58
     aval
    -0.57
    foundland
    -0.57
    frac
    -0.55
    âĵĺ
    -0.55
    robe
    -0.55
    asio
    -0.55
    POSITIVE LOGITS
     however
    0.90
     moreover
    0.79
     THERE
    0.72
     Amend
    0.70
     unlike
    0.67
     meanwhile
    0.65
     therefore
    0.64
    amina
    0.62
     there
    0.61
     Chak
    0.60
    Activations Density 0.126%

    No Known Activations