© 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. 8-RES-JB
    11. 16824
    Prev
    Next
    INDEX
    Explanations

    the word "people" occurring in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to general opinions or experiences of people

    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
    ILA
    -0.72
     Deadly
    -0.71
    MpServer
    -0.63
     Loch
    -0.63
    selection
    -0.62
     Redemption
    -0.61
    rompt
    -0.60
     Sanctuary
    -0.60
     holiest
    -0.60
    =]
    -0.59
    POSITIVE LOGITS
     instinctively
    1.01
     prefer
    1.01
     perceive
    0.99
     confuse
    0.97
     assume
    0.93
     realize
    0.92
     equate
    0.91
     agree
    0.90
     realise
    0.89
     alike
    0.89
    Activations Density 0.135%

    No Known Activations