© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 19741
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "it" and its associated verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     owes
    -0.78
     subscrib
    -0.76
    sb
    -0.71
     owe
    -0.65
    rc
    -0.63
     Patron
    -0.60
    sha
    -0.57
     ought
    -0.56
     LAT
    -0.56
     newsp
    -0.56
    POSITIVE LOGITS
     raining
    1.33
     unclear
    1.01
     obvious
    0.93
     easier
    0.93
     clear
    0.91
     harder
    0.90
     evident
    0.89
     impossible
    0.89
     difficult
    0.84
     possible
    0.82
    Activations Density 0.313%

    No Known Activations