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. 10-RES-JB
    6. 14203
    Prev
    Next
    INDEX
    Explanations

    phrases related to percentages or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate numerical data or statistics related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     predec
    -0.74
     istg
    -0.69
     disapp
    -0.65
    taboola
    -0.64
     withd
    -0.63
    icultural
    -0.62
    bs
    -0.61
     spons
    -0.59
    oda
    -0.59
    lication
    -0.58
    POSITIVE LOGITS
     them
    0.84
     Nine
    0.77
     THEM
    0.74
     those
    0.74
     nine
    0.72
     Finland
    0.70
     these
    0.69
     every
    0.69
     eleven
    0.68
     thirteen
    0.68
    Activations Density 0.059%

    No Known Activations