© 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. 8399
    Prev
    Next
    INDEX
    Explanations

    co-occurring words in sentences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of blame or accountability in a context that suggests dispute or contention

    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
     sugg
    -0.91
     conclud
    -0.85
     explan
    -0.81
     assum
    -0.79
     exha
    -0.76
     reluct
    -0.76
     obser
    -0.75
     suscept
    -0.74
     discretionary
    -0.72
     ess
    -0.71
    POSITIVE LOGITS
     Pigs
    0.89
     Disneyland
    0.80
     Crist
    0.80
     Kobe
    0.79
     Jimmy
    0.78
     Elvis
    0.76
     Beyon
    0.76
    HAHAHAHA
    0.75
    oba
    0.74
     Kanye
    0.74
    Activations Density 1.012%

    No Known Activations