© 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. 8-RES-JB
    11. 22683
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was" in the text

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs indicating states of being or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Footnote
    -0.69
    Dialogue
    -0.65
    arta
    -0.65
    resp
    -0.63
     Mountains
    -0.62
     Fighters
    -0.62
     References
    -0.62
     HAVE
    -0.61
     IMAGES
    -0.61
     Anger
    -0.61
    POSITIVE LOGITS
     conceived
    1.31
     originally
    1.24
     born
    1.19
    hes
    1.08
     instrumental
    1.02
    wolves
    1.00
     founded
    1.00
     awarded
    1.00
     initially
    0.99
     able
    0.96
    Activations Density 0.308%

    No Known Activations