Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20385
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to personal beliefs and actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iHUD
    -0.66
    Morgan
    -0.65
    Dash
    -0.62
    EStreamFrame
    -0.62
     Morgan
    -0.60
    gery
    -0.60
     è£ıè¦ļéĨĴ
    -0.60
     Reloaded
    -0.59
    struction
    -0.56
    dash
    -0.56
    POSITIVE LOGITS
     perceive
    1.27
    're
    1.00
     eat
    0.98
     consume
    0.93
     want
    0.92
     deem
    0.91
     love
    0.91
     believe
    0.90
     crave
    0.89
     cherish
    0.89
    Activations Density 0.126%

    No Known Activations