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. 6-RES-JB
    6. 2356
    Prev
    Next
    INDEX
    Explanations

    names that end with 'eng'

    oai_token-act-pair · gpt-3.5-turbo

    words related to engineering or engineers

    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
    IFIED
    -0.72
    staking
    -0.68
    tera
    -0.68
    cloth
    -0.68
     Skydragon
    -0.67
    ifications
    -0.67
    âķIJ
    -0.64
    numbered
    -0.64
    pine
    -0.64
    \/\/
    -0.64
    POSITIVE LOGITS
    iment
    1.01
    lishes
    0.98
    ravings
    0.96
    raved
    0.93
    thening
    0.91
    eng
    0.89
    oing
    0.86
    iments
    0.84
    roup
    0.83
    lasses
    0.83
    Activations Density 0.017%

    No Known Activations