© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1648
    Prev
    Next
    INDEX
    Explanations

    phrases related to journeys and quests

    oai_token-act-pair · gpt-3.5-turbo

    titles or phrases related to entertainment, particularly those that include numerical or descriptive elements

    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
    untled
    -0.63
    à¨
    -0.61
    à©
    -0.61
     tempting
    -0.57
    vasive
    -0.53
     hiber
    -0.52
     surplus
    -0.50
     unusually
    -0.50
    aples
    -0.49
    growing
    -0.49
    POSITIVE LOGITS
    !.
    1.07
     Remix
    0.99
    _.
    0.97
    .).
    0.93
    !".
    0.90
    }.
    0.88
     respectively
    0.85
    ]."
    0.81
    ''.
    0.81
    ONSORED
    0.80
    Activations Density 0.790%

    No Known Activations