© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10437
    Prev
    Next
    INDEX
    Explanations

    contractions of 'have' followed by the number 9

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I've" indicating personal experience or ownership

    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
     separates
    -0.64
    eem
    -0.63
    Reviewer
    -0.62
    atile
    -0.59
     smokes
    -0.57
    imately
    -0.57
    outer
    -0.57
    izes
    -0.56
     manifests
    -0.56
     denotes
    -0.56
    POSITIVE LOGITS
     been
    1.33
     Been
    1.23
     gotta
    1.20
    been
    1.17
     gotten
    1.11
     got
    1.08
     gone
    1.01
     done
    0.89
    gotten
    0.87
     begun
    0.85
    Activations Density 0.033%

    No Known Activations