© 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. 6-RES-JB
    11. 11666
    Prev
    Next
    INDEX
    Explanations

    elements related to interacting with online content, such as sending messages or sharing ideas

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceous
    -0.79
    inki
    -0.78
    ulate
    -0.75
    iant
    -0.74
    acies
    -0.74
    redd
    -0.73
    interstitial
    -0.73
    ilit
    -0.73
    oids
    -0.73
    ulation
    -0.72
    POSITIVE LOGITS
    âĢ¢âĢ¢
    1.06
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.99
    ··
    0.95
    Ħ¢
    0.84
    ||||
    0.80
    Þ
    0.71
    ËĪ
    0.69
    ĭ
    0.68
    ICLE
    0.68
    İĭ
    0.68
    Activations Density 0.034%

    No Known Activations