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. 1-RES-JB
    6. 7931
    Prev
    Next
    INDEX
    Explanations

    words related to physical injuries or impacts

    oai_token-act-pair · gpt-3.5-turbo

    words that begin with "er" or are related to errors or discrepancies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itionally
    -0.78
    ership
    -0.71
    parency
    -0.70
    IGHTS
    -0.68
    OUNT
    -0.66
    hips
    -0.64
    TPPStreamerBot
    -0.63
    INESS
    -0.63
    erness
    -0.63
    itional
    -0.62
    POSITIVE LOGITS
     er
    0.99
    aser
    0.94
    asures
    0.86
    asure
    0.83
    ogenous
    0.76
    asing
    0.74
    rett
    0.73
    odox
    0.73
    rant
    0.73
     awa
    0.72
    Activations Density 0.006%

    No Known Activations