© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24453
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive determiners indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their corresponding actions or statements

    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
    uzzle
    -0.77
    ibaba
    -0.76
     CrossRef
    -0.75
    ilial
    -0.69
    igslist
    -0.68
    Prev
    -0.67
    daq
    -0.67
    iferation
    -0.65
    emort
    -0.65
    iverse
    -0.65
    POSITIVE LOGITS
     colleague
    1.36
     colleagues
    1.27
     predecessor
    1.19
     nephew
    1.13
     own
    1.13
     superiors
    1.12
     client
    1.10
     constituents
    1.09
     counterparts
    1.07
     predecessors
    1.07
    Activations Density 0.192%

    No Known Activations