© 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. 8-RES-JB
    11. 8133
    Prev
    Next
    INDEX
    Explanations

    concepts related to risks or threats

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate risks or serious consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ECA
    -0.68
    Avg
    -0.65
    eatures
    -0.62
    ãģ®é
    -0.62
     Rodrig
    -0.60
     Tens
    -0.59
    cius
    -0.59
     cheers
    -0.57
    æ©
    -0.56
    Newsletter
    -0.56
    POSITIVE LOGITS
     impending
    1.01
     apocalypse
    0.99
     imminent
    0.87
     retribution
    0.87
     repercussions
    0.86
     someday
    0.86
     reperc
    0.81
     contag
    0.80
    thood
    0.79
     relapse
    0.79
    Activations Density 0.553%

    No Known Activations