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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 9794
    Prev
    Next
    INDEX
    Explanations

    words related to the drug experience or drug culture

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tripping, physical encounters, or challenges

    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
    âĢ
    -0.88
    ¶
    -0.75
     âĢ
    -0.73
    âĸł
    -0.64
    ?ãĢį
    -0.62
     ÂŃ
    -0.59
    âĢł
    -0.58
    ÂŃ
    -0.57
    .—
    -0.57
    âĸ
    -0.56
    POSITIVE LOGITS
     wiser
    0.42
     mushroom
    0.41
     marvelous
    0.41
     etc
    0.41
     greatly
    0.41
     and
    0.40
     explosion
    0.40
     forever
    0.39
    itent
    0.39
     tremendously
    0.39
    Activations Density 1.733%

    No Known Activations