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. 21870
    Prev
    Next
    INDEX
    Explanations

    verbs expressing cessation or interruption of action

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express cessation or the act of stopping

    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
    ighth
    -0.80
    Sov
    -0.79
    ammy
    -0.77
    é¾įåĸļ士
    -0.73
    ety
    -0.71
    uries
    -0.69
    aths
    -0.68
    arov
    -0.67
    VERTISEMENT
    -0.66
    acht
    -0.66
    POSITIVE LOGITS
     bothering
    1.01
    watching
    0.98
    gap
    0.95
    watch
    0.92
     breathing
    0.82
     raining
    0.82
     smoking
    0.81
     worrying
    0.80
    ŃĶ
    0.80
     abruptly
    0.79
    Activations Density 0.038%

    No Known Activations