Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 20136
    Prev
    Next
    INDEX
    Explanations

    numerical values typically used in a list or sequence

    oai_token-act-pair · gpt-3.5-turbo

    numerical references and possibly data related to legal or historical statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    milo
    -0.70
     ,"
    -0.68
     cooperative
    -0.63
     ',
    -0.60
     comprom
    -0.60
     \"
    -0.57
    anooga
    -0.56
     ",
    -0.56
    cius
    -0.55
     experien
    -0.55
    POSITIVE LOGITS
    ][
    2.06
    ]
    1.85
    ])
    1.52
    ]"
    1.50
    ].
    1.44
    ]).
    1.40
    ],[
    1.39
    ],
    1.38
    ]+
    1.36
    ]:
    1.35
    Activations Density 0.040%

    No Known Activations