© 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. 9-RES-JB
    11. 8939
    Prev
    Next
    INDEX
    Explanations

    sentences discussing the state or condition of things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate changes or shifts in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rac
    -0.70
    pora
    -0.69
    Joined
    -0.69
    lication
    -0.67
    ELD
    -0.66
    sole
    -0.63
    fill
    -0.63
     presence
    -0.63
    DNA
    -0.63
    nor
    -0.63
    POSITIVE LOGITS
     downhill
    0.86
     spir
    0.83
     unravel
    0.79
     spiral
    0.75
     escalated
    0.75
     alright
    0.72
     differently
    0.72
     escalate
    0.72
     happening
    0.71
     deteriorating
    0.71
    Activations Density 0.165%

    No Known Activations