Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 18712
    Prev
    Next
    INDEX
    Explanations

    numeric measurements

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express measurements or specifications

    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
     advis
    -0.78
     worsh
    -0.65
     chained
    -0.63
     maiden
    -0.63
     performer
    -0.61
     trouble
    -0.61
     particip
    -0.60
     enrollment
    -0.60
     flooding
    -0.60
     purse
    -0.60
    POSITIVE LOGITS
    5
    1.44
    75
    1.32
    0
    1.31
    25
    1.27
    8
    1.23
    66666666
    1.22
    875
    1.19
    000000
    1.17
    6
    1.16
    3333
    1.15
    Activations Density 0.085%

    No Known Activations