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. 23650
    Prev
    Next
    INDEX
    Explanations

    precision-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accuracy and measurement

    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
    gow
    -0.71
    ifer
    -0.70
     Ticket
    -0.68
    arie
    -0.67
    ifest
    -0.66
    ivan
    -0.66
    ews
    -0.65
     Login
    -0.65
     financially
    -0.65
    Corp
    -0.65
    POSITIVE LOGITS
     precision
    3.74
     Precision
    2.34
    cision
    1.85
     accuracy
    1.70
     specificity
    1.53
     precise
    1.45
     accur
    1.26
     dexterity
    1.25
     certainty
    1.23
     sophistication
    1.17
    Activations Density 0.015%

    No Known Activations