© 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. 11-RES-JB
    11. 3629
    Prev
    Next
    INDEX
    Explanations

    the word "not" and followed by contrasting information or ideas

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating something is not true or not happening

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.80
    ãĤ·ãĥ£
    -0.73
    assian
    -0.68
    rift
    -0.68
    ÃŁ
    -0.63
    atari
    -0.63
    iesel
    -0.63
    company
    -0.61
    leanor
    -0.59
    addy
    -0.59
    POSITIVE LOGITS
     necessarily
    1.35
     enough
    1.03
    etheless
    1.02
     anymore
    0.96
     everyone
    0.94
    icable
    0.93
    icably
    0.91
    withstanding
    0.90
     everybody
    0.89
    eworthy
    0.89
    Activations Density 0.054%

    No Known Activations