© 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. 7-RES-JB
    11. 21349
    Prev
    Next
    INDEX
    Explanations

    mentions of news headlines related to various topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rare or notable events related to animals or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.97
    Newsletter
    -0.84
    Story
    -0.67
     thereafter
    -0.67
    };
    -0.65
    âĢ¢âĢ¢
    -0.63
    Shape
    -0.62
    ];
    -0.62
    Layer
    -0.61
     };
    -0.57
    POSITIVE LOGITS
    reetings
    0.63
    ayson
    0.63
     embattled
    0.61
    andals
    0.59
    earable
    0.54
    uden
    0.54
     bestselling
    0.54
     nomine
    0.53
    ASHINGTON
    0.53
    hester
    0.53
    Activations Density 1.907%

    No Known Activations