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. 1973
    Prev
    Next
    INDEX
    Explanations

    personal names that end with the letter 'er'

    oai_token-act-pair · gpt-3.5-turbo

    words related to individuals in various roles or occupations, particularly those ending with 'er'

    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
    ĸļ
    -0.67
     Lovecraft
    -0.66
    ELS
    -0.64
     trump
    -0.60
     Shannon
    -0.59
     Mayweather
    -0.59
    eenth
    -0.58
     Floyd
    -0.57
     Bridges
    -0.57
    aspers
    -0.57
    POSITIVE LOGITS
    rors
    0.89
    unning
    0.86
    aton
    0.86
    usalem
    0.86
    itage
    0.85
    uner
    0.85
    cial
    0.84
    rera
    0.83
    nery
    0.83
    lein
    0.81
    Activations Density 0.039%

    No Known Activations