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. 9-RES-JB
    6. 14469
    Prev
    Next
    INDEX
    Explanations

    words related to numbers denoting quantity or count

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, particularly those related to quantities of people or items in the millions or billions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dating
    -0.71
    ourage
    -0.70
    cade
    -0.69
    bara
    -0.66
    Dialogue
    -0.66
    apult
    -0.66
    icut
    -0.64
    anwhile
    -0.64
    CHR
    -0.63
    alid
    -0.63
    POSITIVE LOGITS
     dollars
    1.26
     hectares
    1.17
     acres
    1.12
     pounds
    1.11
     tonnes
    1.09
     gallons
    1.07
    aires
    1.05
     euros
    1.04
     litres
    1.03
     sq
    1.01
    Activations Density 0.086%

    No Known Activations