© 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. 10198
    Prev
    Next
    INDEX
    Explanations

    phrases related to signing up for events or services

    oai_token-act-pair · gpt-3.5-turbo

    administrative and organizational terms related to sign-ups and updates

    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
    ":[
    -0.71
    ":"
    -0.63
    uyomi
    -0.62
     alike
    -0.59
     broader
    -0.59
    \":
    -0.58
     easing
    -0.57
    Ń·
    -0.57
     GOODMAN
    -0.56
    ":
    -0.55
    POSITIVE LOGITS
    Unknown
    0.76
    unknown
    0.65
     Requires
    0.63
     Retrieved
    0.61
     [-
    0.61
     Unknown
    0.61
    ructose
    0.60
     Edition
    0.60
     Received
    0.60
     Concepts
    0.60
    Activations Density 0.338%

    No Known Activations