© 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. 1-RES-JB
    11. 898
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences within brackets

    oai_token-act-pair · gpt-3.5-turbo

    instances of the closing bracket character in the text

    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
    Ń·
    -0.95
    ĸļ
    -0.93
    etsy
    -0.77
    »Ĵ
    -0.75
    sts
    -0.73
     arte
    -0.71
    iae
    -0.70
    uka
    -0.70
    ĻĤ
    -0.70
    ãĤ©
    -0.69
    POSITIVE LOGITS
    ...]
    0.97
    ],
    0.94
    worthiness
    0.94
     ]
    0.91
    ])
    0.86
    ].
    0.85
    >]
    0.84
    âĢ¦]
    0.83
    ][
    0.81
    ]
    0.80
    Activations Density 0.052%

    No Known Activations