© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 7147
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets indicating a specific kind of information or operation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, primarily parentheses and brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hor
    -0.88
    ´
    -0.79
    stra
    -0.76
    ide
    -0.76
    rament
    -0.75
    ku
    -0.75
    azing
    -0.74
    bor
    -0.74
    rum
    -0.72
    ton
    -0.72
    POSITIVE LOGITS
    )))
    1.38
    ))))
    1.15
    ))
    1.11
    ])
    0.99
    ]).
    0.97
    ]),
    0.94
    )),
    0.94
    )).
    0.93
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.87
    >]
    0.85
    Activations Density 0.023%

    No Known Activations