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

    Neuronpedia

    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. 8-RES-JB
    11. 7891
    Prev
    Next
    INDEX
    Explanations

    contractions with the letter 's

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "It’s" or variations thereof that indicate a statement or observation

    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
    ESE
    -0.79
    ren
    -0.72
    igraph
    -0.69
    nel
    -0.69
    scope
    -0.68
    ollow
    -0.67
    %%
    -0.67
    DS
    -0.67
    stad
    -0.66
    umbnail
    -0.66
    POSITIVE LOGITS
     gonna
    1.16
     unclear
    1.15
     gotta
    1.15
     been
    1.08
     impossible
    1.03
     doubtful
    1.01
     worth
    1.01
     easy
    0.99
     gotten
    0.97
     got
    0.95
    Activations Density 0.075%

    No Known Activations