© 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. 8-RES-JB
    11. 20305
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Kirk"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kirk."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outgoing
    -0.65
     disadvant
    -0.65
     rul
    -0.61
     acknow
    -0.60
     delinquent
    -0.59
     birthday
    -0.59
     reversible
    -0.59
     unheard
    -0.58
    ++++
    -0.58
     corrid
    -0.58
    POSITIVE LOGITS
    patrick
    1.83
    wall
    1.06
    bys
    1.02
    land
    1.01
    wood
    1.01
    ham
    0.97
    istani
    0.95
    lessly
    0.95
    lands
    0.95
     Cousins
    0.93
    Activations Density 0.033%

    No Known Activations