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. 0-RES-JB
    6. 14254
    Prev
    Next
    INDEX
    Explanations

    phrases related to directives or instructions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of "shutdown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ici
    -0.67
     liter
    -0.65
     speaking
    -0.63
    ĸļ
    -0.61
     Ot
    -0.59
    OLOG
    -0.59
     Applied
    -0.58
     pres
    -0.58
     Oral
    -0.57
    ITIES
    -0.56
    POSITIVE LOGITS
    down
    4.09
    downs
    3.21
    Down
    2.34
    DOWN
    2.23
     Down
    1.76
     downs
    1.71
     down
    1.61
    up
    1.53
     DOWN
    1.42
    ups
    1.31
    Activations Density 0.012%

    No Known Activations