© 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. 3-RES-JB
    11. 10717
    Prev
    Next
    INDEX
    Explanations

    instances where the word "inline" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to specific inline elements or structures in programming and noteworthy individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emouth
    -0.90
    ð
    -0.80
    ocene
    -0.80
    gewater
    -0.77
    ebus
    -0.74
    perture
    -0.72
    quila
    -0.72
    itect
    -0.70
    ĨĴ
    -0.70
     actionGroup
    -0.69
    POSITIVE LOGITS
    forth
    0.73
     prescribing
    0.69
    jet
    0.67
    CHAPTER
    0.66
    BY
    0.66
    oute
    0.65
    jad
    0.65
     skating
    0.64
     relent
    0.63
     takeoff
    0.63
    Activations Density 0.020%

    No Known Activations