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. 15240
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements

    oai_token-act-pair · gpt-3.5-turbo

    measurements and specifications related to physical objects

    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
     trolls
    -0.71
     scapego
    -0.70
     imperson
    -0.68
     unsub
    -0.66
     reinstated
    -0.65
     caric
    -0.65
     Reyes
    -0.63
     agre
    -0.63
     substitutes
    -0.62
    rompt
    -0.62
    POSITIVE LOGITS
    Maximum
    1.35
     Maximum
    1.27
     Length
    1.25
     Width
    1.22
     Average
    1.21
     Dimensions
    1.19
     Capacity
    1.19
     Weight
    1.18
     maximum
    1.17
    maximum
    1.17
    Activations Density 0.219%

    No Known Activations