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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 22456
    Prev
    Next
    INDEX
    Explanations

    internet-related or technical terms and information mentioned in text formats

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or formal notices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.69
    milo
    -0.64
     Come
    -0.64
    alties
    -0.63
     ACTIONS
    -0.63
    conservancy
    -0.60
    morrow
    -0.59
     {{
    -0.59
    tis
    -0.58
    sov
    -0.57
    POSITIVE LOGITS
    ]
    1.62
    ]"
    1.49
    ?]
    1.49
    ]:
    1.43
    ],
    1.36
    ],"
    1.34
    â̦]
    1.30
    ][
    1.27
    ãĢij
    1.25
    ']
    1.24
    Activations Density 0.221%

    No Known Activations