© 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. 3121
    Prev
    Next
    INDEX
    Explanations

    phrases starting with special characters '&' and digits

    oai_token-act-pair · gpt-3.5-turbo

    instances of the ampersand symbol (&)

    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
    etheless
    -0.67
     orche
    -0.66
    owicz
    -0.63
     obst
    -0.63
     virt
    -0.62
    ifying
    -0.61
     transit
    -0.60
     overwhelmingly
    -0.60
    ogene
    -0.59
    lessness
    -0.58
    POSITIVE LOGITS
    Bs
    1.11
    Cs
    1.11
    HI
    1.05
    RD
    0.94
    NW
    0.94
    RH
    0.94
    Ds
    0.94
    Es
    0.94
    CT
    0.93
    RT
    0.93
    Activations Density 0.026%

    No Known Activations