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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2-RES-JB
    6. 13053
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns related to ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unsure
    -0.61
    bender
    -0.59
     Pwr
    -0.59
    PLA
    -0.55
     Recomm
    -0.54
    /+
    -0.54
    Section
    -0.53
     Enhancement
    -0.53
    AAAA
    -0.53
    Texture
    -0.53
    POSITIVE LOGITS
     own
    1.43
     respective
    0.94
     newfound
    0.87
    self
    0.85
     favourite
    0.85
     knees
    0.83
    selves
    0.82
     entire
    0.81
     preferred
    0.81
     assailant
    0.80
    Activations Density 0.486%

    No Known Activations