© 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. 12898
    Prev
    Next
    INDEX
    Explanations

    references to governmental or organizational policies

    oai_token-act-pair · gpt-3.5-turbo

    references to government policies

    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
    ITNESS
    -0.85
    issan
    -0.85
    athan
    -0.75
    ãĤ¨ãĥ«
    -0.73
    Vel
    -0.70
    Rocket
    -0.69
     Brotherhood
    -0.69
     Sabha
    -0.69
    avez
    -0.69
     Flavoring
    -0.67
    POSITIVE LOGITS
     policies
    1.11
     prescriptions
    0.91
     Policies
    0.90
     policy
    0.90
     preferences
    0.84
     stances
    0.83
    olicy
    0.82
    policy
    0.79
     governing
    0.79
    aroo
    0.77
    Activations Density 0.012%

    No Known Activations