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. 1-RES-JB
    6. 8522
    Prev
    Next
    INDEX
    Explanations

    locations or settings described in text

    oai_token-act-pair · gpt-3.5-turbo

    the repeated usage of the phrase "in" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llor
    -0.70
    CLASSIFIED
    -0.68
     convol
    -0.61
     showc
    -0.60
     contag
    -0.58
    MODE
    -0.57
    channelAvailability
    -0.57
    SourceFile
    -0.56
    bryce
    -0.56
     guiActiveUn
    -0.56
    POSITIVE LOGITS
     lieu
    1.23
    clus
    1.20
     accordance
    1.16
    ordinate
    1.09
     conjunction
    1.08
    clusions
    1.06
    patient
    1.03
    animate
    1.03
    clusively
    1.02
    roads
    1.02
    Activations Density 0.940%

    No Known Activations