© 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. 10-RES-JB
    11. 10772
    Prev
    Next
    INDEX
    Explanations

    phrases related to dependency and consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the importance of support and guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.63
    enser
    -0.62
    Fla
    -0.61
    Specifically
    -0.61
    FINE
    -0.60
    FTWARE
    -0.60
    AKING
    -0.59
     advertis
    -0.59
     Compensation
    -0.58
    soDeliveryDate
    -0.58
    POSITIVE LOGITS
     starve
    0.99
     doomed
    0.97
     stagn
    0.94
     deterior
    0.91
     risk
    0.90
     misunderstand
    0.89
     harm
    0.88
     jeopard
    0.87
     ruin
    0.86
     negatively
    0.85
    Activations Density 0.227%

    No Known Activations