© 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. 11-RES-JB
    11. 22571
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology companies and software updates

    oai_token-act-pair · gpt-3.5-turbo

    key elements related to video games and their development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jen
    -1.02
     eleph
    -0.93
    ARDIS
    -0.84
     Meredith
    -0.83
     Carth
    -0.83
     Giles
    -0.83
    Scotland
    -0.82
    psc
    -0.81
    etheus
    -0.81
    Aust
    -0.81
    POSITIVE LOGITS
     Capcom
    1.93
     Brawl
    1.76
     Melee
    1.70
     Ryu
    1.69
     Chun
    1.62
     Smash
    1.62
     Tek
    1.50
     arcade
    1.45
     Mortal
    1.37
     Yoshi
    1.35
    Activations Density 0.195%

    No Known Activations