© 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. 9-RES-JB
    11. 13127
    Prev
    Next
    INDEX
    Explanations

    consecutive words with some common themes of lessons or learning

    oai_token-act-pair · gpt-3.5-turbo

    instances of lessons learned or key conclusions in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.56
    ]."
    -0.52
    ."[
    -0.50
     ."
    -0.49
     ];
    -0.48
    .[
    -0.47
     thereof
    -0.46
    ];
    -0.46
    }.
    -0.45
    ".[
    -0.44
    POSITIVE LOGITS
     Profile
    0.62
     meanwhile
    0.60
    ':
    0.55
     Edit
    0.52
     FANTASY
    0.51
    %:
    0.49
    :
    0.49
     Explan
    0.49
    odore
    0.48
     Definition
    0.47
    Activations Density 1.956%

    No Known Activations