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. 8576
    Prev
    Next
    INDEX
    Explanations

    phrases related to news headlines

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or actions in sports and current affairs

    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
     ));
    -0.64
     fortunate
    -0.60
     behavi
    -0.59
    reporting
    -0.57
    ibaba
    -0.55
    milo
    -0.53
     blight
    -0.52
    onga
    -0.51
     upt
    -0.49
     fortun
    -0.49
    POSITIVE LOGITS
    ]
    3.04
    ?]
    2.81
    !]
    2.80
    .]
    2.72
    ']
    2.72
    ]"
    2.72
    :]
    2.65
    ...]
    2.64
    ]:
    2.61
    ].
    2.59
    Activations Density 0.205%

    No Known Activations