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. 0-RES-JB
    6. 5931
    Prev
    Next
    INDEX
    Explanations

    mentions of the car manufacturer Mitsubishi

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or characters related to a narrative or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     checkpoints
    -0.69
     hierarch
    -0.68
     confirmation
    -0.68
     protection
    -0.66
     contr
    -0.65
     cle
    -0.65
     free
    -0.65
     competition
    -0.64
     ticket
    -0.63
     services
    -0.63
    POSITIVE LOGITS
    ishi
    4.76
    uchi
    1.44
    ogi
    1.17
    ichi
    1.16
    aja
    1.13
    iki
    1.12
    ataka
    1.11
    ashi
    1.11
    imaru
    1.10
    amiya
    1.08
    Activations Density 0.018%

    No Known Activations