© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7297
    Prev
    Next
    INDEX
    Explanations

    statements issued jointly by multiple parties

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to joint actions or collaborations among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylon
    -0.75
    ilk
    -0.73
    aters
    -0.70
    worms
    -0.68
    eno
    -0.64
    aghetti
    -0.63
    holes
    -0.63
    acha
    -0.62
    gins
    -0.60
    conservancy
    -0.60
    POSITIVE LOGITS
     venture
    1.10
     ventures
    1.05
     effort
    0.91
     chiefs
    0.83
     declaration
    0.79
    ness
    0.77
     Venture
    0.75
     fundraising
    0.73
    venture
    0.71
    operation
    0.71
    Activations Density 0.028%

    No Known Activations