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. 3-RES-JB
    6. 7911
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of serving or being deserving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to service or servitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    axter
    -0.64
     procedural
    -0.62
     ][
    -0.61
    hran
    -0.60
     structured
    -0.59
    raid
    -0.58
     GOODMAN
    -0.58
    aha
    -0.58
    sett
    -0.57
     finalized
    -0.57
    POSITIVE LOGITS
    erve
    1.12
    erves
    1.10
    erved
    0.97
    erving
    0.74
    llan
    0.73
    rl
    0.73
    warm
    0.71
     Serve
    0.70
    lig
    0.70
    erv
    0.68
    Activations Density 0.018%

    No Known Activations