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. 8-RES-JB
    6. 5829
    Prev
    Next
    INDEX
    Explanations

    the word "Nam" followed by a single character for a proper noun or abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or individual, particularly "Nam."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posit
    -0.66
     grounding
    -0.59
     inference
    -0.59
     inhib
    -0.59
     almonds
    -0.59
     understatement
    -0.58
     yeast
    -0.58
    DW
    -0.58
     inhibition
    -0.57
    HEAD
    -0.57
    POSITIVE LOGITS
    ibia
    1.15
    eless
    1.05
    azing
    1.00
    pered
    0.93
    aji
    0.93
    pty
    0.92
    essage
    0.90
    ankind
    0.89
    achu
    0.89
    our
    0.86
    Activations Density 0.029%

    No Known Activations