© 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. 18647
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or beliefs about different subjects

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating future possibilities or hypothetical scenarios

    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
     Sandwich
    -0.72
    Reloaded
    -0.67
     Surveillance
    -0.63
     Cance
    -0.62
    soDeliveryDate
    -0.61
     Replacement
    -0.60
    ONSORED
    -0.59
     Modified
    -0.59
     Reborn
    -0.58
    forms
    -0.57
    POSITIVE LOGITS
     attest
    1.60
     doubtless
    1.25
     rejoice
    1.22
     appreciate
    1.17
     cringe
    1.15
     understandably
    1.14
     gladly
    1.11
     recognize
    1.09
     scoff
    1.09
     undoubtedly
    1.07
    Activations Density 0.158%

    No Known Activations