© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12888
    Prev
    Next
    INDEX
    Explanations

    references to R&B music and related subjects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the ampersand symbol "&" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessness
    -0.65
    ogene
    -0.59
     obst
    -0.58
     orche
    -0.58
    mit
    -0.57
    etheless
    -0.56
     aur
    -0.56
     mattered
    -0.56
     overwhelmingly
    -0.55
    upon
    -0.55
    POSITIVE LOGITS
    Cs
    1.31
    Bs
    1.24
    Ds
    1.10
    RD
    1.07
    HI
    1.06
    W
    1.04
    Ws
    1.04
    RH
    1.04
    C
    1.03
    Es
    1.03
    Activations Density 0.023%

    No Known Activations