© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 17552
    Prev
    Next
    INDEX
    Explanations

    words with a negation prefix followed by an adjective

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptions or qualifiers related to situations or actions

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.74
     showc
    -0.72
     uninterrupted
    -0.66
    Ͻ
    -0.64
    imeter
    -0.62
    ãĥ¼ãĥĨãĤ£
    -0.61
     Strongh
    -0.61
    ventory
    -0.59
    ĸļ
    -0.58
    eret
    -0.57
    POSITIVE LOGITS
    icable
    0.84
    yet
    0.75
    withstanding
    0.71
    ables
    0.67
    atives
    0.66
     coinc
    0.64
     mention
    0.64
    gre
    0.62
    ches
    0.62
    cial
    0.62
    Activations Density 0.110%

    No Known Activations