© 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. 4-RES-JB
    11. 10853
    Prev
    Next
    INDEX
    Explanations

    phrases related to neglect, ignorance, or turning a blind eye to something

    oai_token-act-pair · gpt-3.5-turbo

    references to blindness or being blind to something

    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
    çīĪ
    -0.74
    ¢
    -0.72
    lez
    -0.67
    anton
    -0.66
     Wonderful
    -0.65
    ciation
    -0.65
     Emin
    -0.64
    APH
    -0.64
     ILCS
    -0.64
     ingred
    -0.64
    POSITIVE LOGITS
    utsche
    0.79
     leash
    0.64
     lest
    0.63
    notice
    0.62
    weak
    0.61
    ociate
    0.59
     vest
    0.58
     clinging
    0.58
     unse
    0.58
     knit
    0.58
    Activations Density 0.347%

    No Known Activations