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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5688
    Prev
    Next
    INDEX
    Explanations

    phrases related to death

    oai_token-act-pair · gpt-3.5-turbo

    instances of a special character or symbol

    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
    ioxide
    -0.64
     juggling
    -0.64
    ORK
    -0.61
     winds
    -0.59
     humidity
    -0.54
     midrange
    -0.54
     fly
    -0.53
     runaway
    -0.53
     halves
    -0.53
     transformer
    -0.52
    POSITIVE LOGITS
     âĢ
    3.95
    âĢ
    2.47
    âĢł
    1.60
     **
    1.44
     âĶ
    1.41
    âĢİ
    1.30
     âĹ
    1.28
     â
    1.25
     âĩ
    1.24
     âĪ
    1.22
    Activations Density 0.240%

    No Known Activations