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. 1-RES-JB
    6. 14818
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming, specifically focusing on the abbreviation "CP" and variants of it

    oai_token-act-pair · gpt-3.5-turbo

    references to Consumer Price Index (CPI) and related economic terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hurricanes
    -0.68
    âĸ¬
    -0.67
     Atlantis
    -0.63
     Ravens
    -0.63
     Roses
    -0.62
     Nig
    -0.60
     Semin
    -0.60
    taboola
    -0.60
     Samoa
    -0.59
     Goo
    -0.59
    POSITIVE LOGITS
    CP
    1.06
    ython
    0.99
    odcast
    0.93
    rint
    0.88
    PP
    0.86
    ropri
    0.86
    ocalypse
    0.85
    oint
    0.84
    arser
    0.83
    rompt
    0.83
    Activations Density 0.003%

    No Known Activations