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. 3-RES-JB
    6. 19069
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'value'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of value in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jen
    -0.83
    nee
    -0.72
    ker
    -0.67
     Zimmer
    -0.67
    washer
    -0.66
    riter
    -0.66
    thus
    -0.65
    ni
    -0.65
    stem
    -0.65
    rontal
    -0.65
    POSITIVE LOGITS
     proposition
    1.04
     value
    1.02
     propositions
    0.83
     Value
    0.78
    value
    0.77
     appreciation
    0.74
    Ô
    0.73
     values
    0.73
    Value
    0.71
     judgments
    0.70
    Activations Density 0.020%

    No Known Activations