© 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. 0-RES-JB
    11. 16360
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing or pointing out something important

    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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     merge
    -0.62
     fluor
    -0.59
     duplication
    -0.58
     interchange
    -0.55
     eyed
    -0.55
     neck
    -0.54
     leap
    -0.54
     merits
    -0.53
     judgment
    -0.53
     carb
    -0.53
    POSITIVE LOGITS
    so
    4.14
    sov
    1.60
    sole
    1.58
    SO
    1.57
    soon
    1.50
    se
    1.30
    thus
    1.21
    So
    1.20
     so
    1.12
    son
    1.12
    Activations Density 0.010%

    No Known Activations