© 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. 2-RES-JB
    11. 21754
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "same" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "same."

    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
    omics
    -0.74
    arest
    -0.66
    ashington
    -0.66
    erest
    -0.65
    *=-
    -0.65
    orsi
    -0.64
    ostic
    -0.64
    akings
    -0.63
    redo
    -0.62
    oming
    -0.61
    POSITIVE LOGITS
     exact
    0.90
     thing
    0.85
     vein
    0.85
    rity
    0.82
    nesota
    0.75
     amount
    0.75
     day
    0.73
    same
    0.72
    Same
    0.70
     reason
    0.67
    Activations Density 0.046%

    No Known Activations