© 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. 0-RES-JB
    11. 14664
    Prev
    Next
    INDEX
    Explanations

    special characters and unusual sequences of characters in the text

    oai_token-act-pair · gpt-3.5-turbo

    multiple consecutive bracket characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dak
    -0.69
     Chambers
    -0.63
     Waterloo
    -0.57
     success
    -0.56
    opes
    -0.55
     appreci
    -0.54
     Chattanooga
    -0.53
     Knox
    -0.53
     Go
    -0.52
     Watson
    -0.52
    POSITIVE LOGITS
    ][
    3.88
     ][
    2.40
    ][/
    2.33
    ];
    2.01
    ].
    1.99
    ]
    1.98
    ](
    1.94
    ]:
    1.93
    ]-
    1.93
    ],
    1.89
    Activations Density 0.020%

    No Known Activations