© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 8244
    Prev
    Next
    INDEX
    Explanations

    the word "so" when it is being emphasized or intensifying an action or state

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "so."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropolitan
    -0.63
     glances
    -0.60
     acre
    -0.59
    wreck
    -0.59
     {:
    -0.57
    haven
    -0.51
     Dive
    -0.51
     Northwest
    -0.51
     Arch
    -0.51
     Slide
    -0.50
    POSITIVE LOGITS
    bered
    1.19
    oths
    1.13
    othes
    1.02
    apy
    1.02
    oooo
    1.00
    ooo
    1.00
    zin
    0.97
    othe
    0.94
    oner
    0.94
    oooooooooooooooo
    0.93
    Activations Density 0.120%

    No Known Activations