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. 6-RES-JB
    6. 8588
    Prev
    Next
    INDEX
    Explanations

    expressions related to commitment or loyalty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "fe" and its variations, indicating a focus on words associated with feelings or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sapphire
    -0.69
     Authority
    -0.67
     Shining
    -0.66
     Dominion
    -0.65
     Kurd
    -0.65
    AGE
    -0.65
     Katz
    -0.64
     Crunch
    -0.63
     Salvation
    -0.62
    Org
    -0.62
    POSITIVE LOGITS
    ldom
    1.13
    vered
    1.10
    erate
    0.99
    eking
    0.94
    alty
    0.92
    gging
    0.92
    ld
    0.90
    cking
    0.90
     fe
    0.88
    eling
    0.87
    Activations Density 0.014%

    No Known Activations