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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 15271
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive determiners referring to groups, organizations, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.88
    lehem
    -0.81
    NB
    -0.73
    region
    -0.73
    liga
    -0.72
    byss
    -0.72
    $$
    -0.71
    Balt
    -0.71
    ����
    -0.70
    ÙIJ
    -0.70
    POSITIVE LOGITS
     inability
    1.34
     willingness
    1.26
     motives
    1.25
     reliance
    1.24
     motivations
    1.23
     actions
    1.22
     goal
    1.21
     aim
    1.19
     motto
    1.19
     reluctance
    1.17
    Activations Density 0.226%

    No Known Activations