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. 0-RES-JB
    6. 19423
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning something specifically designed or created for a particular purpose

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of specialized or rented items and modifications

    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
    lly
    -0.81
    politics
    -0.79
    zinski
    -0.70
    thood
    -0.70
    omics
    -0.68
     promotion
    -0.67
    ocide
    -0.66
     Islanders
    -0.64
    ressive
    -0.64
    ynes
    -0.64
    POSITIVE LOGITS
     specially
    2.51
     rented
    2.29
     modified
    1.92
     borrowed
    1.89
     leased
    1.59
     improvised
    1.37
     makeshift
    1.32
     reused
    1.22
    modified
    1.19
     patched
    1.18
    Activations Density 0.025%

    No Known Activations