© 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. 10-RES-JB
    11. 10151
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing personal preferences or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of recommendation or personal opinion

    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
     glimps
    -0.65
     Definitions
    -0.63
     Detail
    -0.62
     Contains
    -0.61
     revelations
    -0.61
    facts
    -0.61
     Investigative
    -0.61
     constit
    -0.60
     contained
    -0.58
     unforeseen
    -0.58
    POSITIVE LOGITS
     recommend
    1.15
     prefer
    0.98
     recommending
    0.95
     gladly
    0.94
     bet
    0.94
     hesitate
    0.92
     endorse
    0.88
    laughs
    0.83
     urge
    0.82
    votes
    0.82
    Activations Density 0.251%

    No Known Activations