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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 18131
    Prev
    Next
    INDEX
    Explanations

    references to a specific name ("Rapp") followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    names of rappers and related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ui
    -0.86
    BG
    -0.74
     meltdown
    -0.74
     cloudy
    -0.67
    holiday
    -0.67
    ÃŃ
    -0.66
    olid
    -0.65
     collapse
    -0.64
     depleted
    -0.64
     helium
    -0.63
    POSITIVE LOGITS
     Rapp
    4.55
     Pike
    1.42
     Gamb
    1.22
     Alb
    1.21
     Grind
    1.16
     rapp
    1.12
     Chick
    1.12
     Cheong
    1.11
     Chatt
    1.08
     Rip
    1.07
    Activations Density 0.030%

    No Known Activations