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. 1-RES-JB
    6. 9881
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "oct" followed by a single digit number

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "oct."

    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
    Interstitial
    -0.84
     Limbaugh
    -0.81
    adder
    -0.76
    ACTED
    -0.76
    ndra
    -0.75
    HCR
    -0.75
    ãģĦ
    -0.74
     Shapiro
    -0.67
    WARE
    -0.67
    ARP
    -0.67
    POSITIVE LOGITS
     oct
    1.37
    oct
    1.34
    opus
    1.14
    ober
    0.99
     Seym
    0.96
    uple
    0.93
    agonal
    0.92
    acles
    0.83
    agon
    0.81
    asus
    0.80
    Activations Density 0.008%

    No Known Activations