© 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. 10206
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote possession or attribution to individuals or groups

    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
    bishop
    -0.71
    BO
    -0.70
    erman
    -0.69
    DT
    -0.69
    Downloadha
    -0.68
    eat
    -0.68
    bro
    -0.68
    ETF
    -0.67
    enny
    -0.67
    EEE
    -0.67
    POSITIVE LOGITS
     sole
    1.26
     livelihood
    1.06
     whereabouts
    1.01
     ancestors
    1.00
     motto
    1.00
     name
    0.99
     identities
    0.99
     job
    0.98
     names
    0.96
     specialty
    0.96
    Activations Density 0.076%

    No Known Activations