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. 6-RES-JB
    6. 2421
    Prev
    Next
    INDEX
    Explanations

    terms related to showrunners and important milestones

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles, particularly in the context of showrunners and milestone events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nap
    -0.75
    EX
    -0.73
    ħ
    -0.71
    į
    -0.70
    ¾
    -0.70
    hold
    -0.69
    VPN
    -0.69
    ĨĴ
    -0.68
    NL
    -0.68
    ²
    -0.68
    POSITIVE LOGITS
    oldemort
    0.81
    sers
    0.76
    worthiness
    0.73
    phrine
    0.73
     Aviv
    0.71
    sbm
    0.70
    aukee
    0.70
    itis
    0.68
    opathy
    0.65
     pageant
    0.64
    Activations Density 0.149%

    No Known Activations