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. 1-RES-JB
    6. 10036
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters

    oai_token-act-pair · gpt-3.5-turbo

    closing brackets or similar symbols in 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
    »Ĵ
    -0.86
    Ń·
    -0.78
    aign
    -0.72
     charm
    -0.70
    ĸļ
    -0.70
    kie
    -0.66
    ĻĤ
    -0.65
    asha
    -0.63
     vain
    -0.62
     brief
    -0.62
    POSITIVE LOGITS
    ],
    1.09
    ...]
    1.07
    ].
    1.05
     Flavoring
    0.88
     ],
    0.88
    ]
    0.86
     ]
    0.83
    ][
    0.80
    ]:
    0.80
    ']
    0.80
    Activations Density 0.013%

    No Known Activations