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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 10194
    Prev
    Next
    INDEX
    Explanations

    information related to availability or access to resources or services

    oai_token-act-pair · gpt-3.5-turbo

    references to the availability of items or information

    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
    ²¾
    -0.88
    kos
    -0.70
    roller
    -0.67
    bey
    -0.65
    respective
    -0.64
    mouse
    -0.64
    mot
    -0.63
    roman
    -0.63
    asus
    -0.62
    mother
    -0.61
    POSITIVE LOGITS
     online
    0.74
     to
    0.71
     via
    0.67
    Cooldown
    0.66
     anywhere
    0.65
    available
    0.65
    isable
    0.64
     for
    0.63
     unrestricted
    0.63
     availability
    0.63
    Activations Density 0.049%

    No Known Activations