© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent organizations and sports teams

    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
    bearing
    -0.61
    margin
    -0.60
    contained
    -0.60
    ashington
    -0.59
    abil
    -0.58
    alone
    -0.58
    izontal
    -0.57
    .''.
    -0.56
    COMPLE
    -0.55
    66666666
    -0.55
    POSITIVE LOGITS
     guy
    0.87
     dudes
    0.85
     guys
    0.80
     vet
    0.79
     dude
    0.77
     psychologist
    0.76
     gentleman
    0.72
     vets
    0.70
     idiots
    0.69
     photographer
    0.69
    Activations Density 0.743%

    No Known Activations