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. 7826
    Prev
    Next
    INDEX
    Explanations

    websites or URLs related to government policies and resources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to policies, governance, and community resources

    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
     earthqu
    -0.81
     pounded
    -0.78
     eleph
    -0.77
     conclud
    -0.75
     compounded
    -0.75
     proport
    -0.74
     brightly
    -0.72
     grossly
    -0.72
     shockingly
    -0.71
     dared
    -0.70
    POSITIVE LOGITS
    /?
    1.92
    /#
    1.82
    /,
    1.78
    /.
    1.72
    /)
    1.70
    /_
    1.66
    /
    1.57
    /"
    1.36
    /$
    1.33
    />
    1.31
    Activations Density 0.101%

    No Known Activations