© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16280
    Prev
    Next
    INDEX
    Explanations

    strings related to software updates and releases

    oai_token-act-pair · gpt-3.5-turbo

    references to software releases or updates and their associated details

    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
    advertising
    -1.02
     telev
    -0.82
    Bey
    -0.82
    iaz
    -0.78
     Beyon
    -0.77
    interstitial
    -0.72
    othing
    -0.72
     Macy
    -0.72
    licks
    -0.72
     Hollow
    -0.71
    POSITIVE LOGITS
     FreeBSD
    1.32
     github
    1.31
     Debian
    1.29
     GitHub
    1.29
     RFC
    1.24
     deprecated
    1.23
     debian
    1.23
     Documentation
    1.22
     GNU
    1.21
     upstream
    1.17
    Activations Density 0.868%

    No Known Activations