© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18810
    Prev
    Next
    INDEX
    Explanations

    aspects related to screen display specifications, such as resolution and size

    oai_token-act-pair · gpt-3.5-turbo

    screen resolutions and specifications

    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
     Nug
    -0.75
    igil
    -0.72
     Briggs
    -0.71
    oleon
    -0.69
    ño
    -0.68
     Hoff
    -0.68
    OUP
    -0.67
    esson
    -0.66
    endas
    -0.65
    kson
    -0.65
    POSITIVE LOGITS
    1080
    1.31
    1920
    1.30
     1280
    1.20
    1024
    1.15
     1920
    1.14
    768
    1.14
     1440
    1.12
     1080
    1.07
     768
    1.05
     1024
    1.05
    Activations Density 0.056%

    No Known Activations