Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20221
    Prev
    Next
    INDEX
    Explanations

    words related to negation or the absence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concepts of absence or lack

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fs
    -0.83
    orks
    -0.77
    flies
    -0.71
    olds
    -0.70
    aughs
    -0.69
    Fs
    -0.68
    lems
    -0.66
     Hits
    -0.66
    assisted
    -0.65
    sym
    -0.64
    POSITIVE LOGITS
     else
    0.89
     hidden
    0.76
     happening
    0.74
     lurking
    0.74
    atable
    0.74
     shameful
    0.72
     poetic
    0.72
     intrinsic
    0.72
     missing
    0.71
     buried
    0.69
    Activations Density 0.052%

    No Known Activations