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. 7-RES-JB
    6. 7085
    Prev
    Next
    INDEX
    Explanations

    numerical expressions or technical code snippets

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, specifically decimal numbers or fractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advis
    -0.70
     defund
    -0.65
     veter
    -0.65
    regation
    -0.64
     sustainability
    -0.63
     proactive
    -0.63
    inarily
    -0.63
     omission
    -0.63
    ogether
    -0.62
     hammer
    -0.62
    POSITIVE LOGITS
    00
    1.25
    0
    1.16
    5
    1.15
    99
    1.15
    jpg
    1.09
    75
    1.09
    5000
    1.09
    25
    1.06
    0000
    1.05
    02
    1.03
    Activations Density 0.083%

    No Known Activations