© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15530
    Prev
    Next
    INDEX
    Explanations

    a specific sequence of letters ('XQ')

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    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
    %);
    -0.65
    .):
    -0.65
    advertisement
    -0.64
     backdrop
    -0.62
    .''.
    -0.61
    ];
    -0.61
    };
    -0.60
    ''.
    -0.59
    ĻĤ
    -0.58
    .�
    -0.58
    POSITIVE LOGITS
     recommends
    0.94
     intends
    0.93
     Productions
    0.93
     employs
    0.90
     refers
    0.90
     has
    0.89
     succeeds
    0.87
     incorporates
    0.85
     achieves
    0.85
     believes
    0.84
    Activations Density 0.566%

    No Known Activations