© 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. 22200
    Prev
    Next
    INDEX
    Explanations

    terms related to analyzing and discussing various subjects, including legal, political, medical, and technological topics

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to decision-making and uncertainties

    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
    ";
    -0.89
    %;
    -0.81
     BUT
    -0.78
    %);
    -0.77
    ';
    -0.75
    !:
    -0.74
    ':
    -0.70
    .;
    -0.70
     But
    -0.69
    !",
    -0.68
    POSITIVE LOGITS
     nonetheless
    1.22
     remains
    1.03
     seems
    1.00
     nevertheless
    1.00
     hasn
    0.94
     shouldn
    0.90
     tends
    0.89
     persists
    0.88
    etheless
    0.87
     isn
    0.87
    Activations Density 0.804%

    No Known Activations