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. 2-RES-JB
    6. 16570
    Prev
    Next
    INDEX
    Explanations

    proper names related to the surname "Cham"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Cham" and "Zam"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     STATES
    -0.77
    uary
    -0.70
     checkout
    -0.67
     seq
    -0.65
    ãģį
    -0.65
     burner
    -0.63
     RAW
    -0.62
     Franz
    -0.61
     Rubin
    -0.61
     inappropriately
    -0.61
    POSITIVE LOGITS
    mit
    1.11
    nesty
    1.08
    essage
    1.08
    ibia
    1.08
    mer
    1.07
    ilitary
    1.07
    borgh
    1.06
    metry
    1.06
    pering
    1.04
    ajo
    1.03
    Activations Density 0.021%

    No Known Activations