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. 0-RES-JB
    6. 10856
    Prev
    Next
    INDEX
    Explanations

    terms related to the abbreviation "PS"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of system or program related to "PS" (likely referring to a policy or procedural system)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Earl
    -0.75
     caravan
    -0.75
     ethn
    -0.72
     Turk
    -0.67
     hed
    -0.67
     daring
    -0.66
     hun
    -0.62
     bod
    -0.62
     adam
    -0.62
     disl
    -0.61
    POSITIVE LOGITS
    PS
    4.25
    ps
    2.18
     PS
    1.93
     PSP
    1.50
    PD
    1.50
    PC
    1.49
    PL
    1.45
    DS
    1.44
    Ps
    1.43
    PM
    1.34
    Activations Density 0.007%

    No Known Activations