© 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
    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. 23042
    Prev
    Next
    INDEX
    Explanations

    phrases related to relaxation or loosening

    oai_token-act-pair · gpt-3.5-turbo

    terms related to releasing or reducing restrictions

    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
     Panda
    -0.70
     Expend
    -0.69
     Warriors
    -0.68
     Barclays
    -0.68
     Metropolitan
    -0.68
     PowerPoint
    -0.67
    FACE
    -0.66
     Omega
    -0.66
     Welsh
    -0.65
     Royale
    -0.65
    POSITIVE LOGITS
    icular
    1.11
    icating
    1.01
    ic
    1.01
    isms
    1.00
    icion
    1.00
    icles
    0.96
    iqu
    0.95
    icated
    0.95
    ening
    0.94
    ip
    0.93
    Activations Density 0.017%

    No Known Activations