Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 22776
    Prev
    Next
    INDEX
    Explanations

    Specific mentions of possessive pronouns "his" and "her."

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to a specific individual

    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
    Downloadha
    -0.87
     largeDownload
    -0.80
    soType
    -0.76
    ngth
    -0.70
    ooks
    -0.68
    AppData
    -0.67
    =-=-=-=-
    -0.66
    govtrack
    -0.65
     Reserved
    -0.64
    inventoryQuantity
    -0.64
    POSITIVE LOGITS
     arrival
    1.39
     departure
    1.31
     arrest
    1.26
     disappearance
    1.19
     appointment
    1.19
     dismissal
    1.18
     inauguration
    1.18
     retirement
    1.17
     death
    1.17
     demise
    1.16
    Activations Density 0.146%

    No Known Activations