© 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. 24005
    Prev
    Next
    INDEX
    Explanations

    references to individuals being observed or referred to

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on" in various contexts

    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
    çĶ°
    -0.77
    amount
    -0.74
    orically
    -0.69
    acters
    -0.66
    ¯¯
    -0.65
    imilation
    -0.64
    dinand
    -0.63
    odies
    -0.63
    holders
    -0.62
    inatory
    -0.61
    POSITIVE LOGITS
    eday
    1.09
    screen
    1.04
     tv
    1.03
     purpose
    1.03
     occasion
    1.02
     Sundays
    0.99
     autop
    0.96
     cue
    0.96
     TV
    0.95
     facebook
    0.94
    Activations Density 0.193%

    No Known Activations