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. 11-RES-JB
    6. 9675
    Prev
    Next
    INDEX
    Explanations

    punctuation marks signaling the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentence structures that indicate uncertainty and conditionals

    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
     guiActiveUnfocused
    -0.76
    ä¸Ĭ
    -0.74
    esh
    -0.70
    coat
    -0.67
    emies
    -0.64
    ware
    -0.62
    å§
    -0.61
    èĢħ
    -0.61
    ç«
    -0.59
    ugi
    -0.59
    POSITIVE LOGITS
     but
    1.09
     nor
    1.07
    but
    1.03
    nor
    0.98
     although
    0.87
     But
    0.84
     specifics
    0.81
     though
    0.80
    perhaps
    0.80
     BUT
    0.79
    Activations Density 0.204%

    No Known Activations