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. 11-RES-JB
    6. 22845
    Prev
    Next
    INDEX
    Explanations

    words related to various industries like mining, fishing, logging, and processing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to natural resource extraction and processing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.80
    iven
    -0.72
    ohm
    -0.70
    IELD
    -0.69
    ifi
    -0.67
     CLIENT
    -0.67
    ĪĴ
    -0.67
    agne
    -0.66
    earable
    -0.66
    urnal
    -0.65
    POSITIVE LOGITS
     plants
    1.29
     facilities
    1.28
     techniques
    1.23
     operations
    1.19
     practices
    1.13
     methods
    1.08
    houses
    1.08
     sites
    1.07
     stations
    1.06
     equipment
    1.03
    Activations Density 0.157%

    No Known Activations