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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 7677
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by possessive determiners

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to people or their belongings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arios
    -0.94
    adobe
    -0.84
    western
    -0.82
    south
    -0.82
    irm
    -0.79
    ACP
    -0.74
    needed
    -0.73
    wrap
    -0.72
    yip
    -0.72
    ocument
    -0.72
    POSITIVE LOGITS
     Majesty
    1.29
     majesty
    1.13
     fingerprints
    0.94
     sensibilities
    0.88
     generosity
    0.88
     own
    0.87
     footsteps
    0.87
     faults
    0.86
     strengths
    0.85
     demeanor
    0.85
    Activations Density 0.286%

    No Known Activations