© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17188
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities that are organized or take place in physical locations, possibly with dates or names included

    oai_token-act-pair · gpt-3.5-turbo

    titles and references to specific films and entertainment-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orically
    -0.85
    cause
    -0.74
     toget
    -0.72
     suspic
    -0.72
    matically
    -0.72
    .).
    -0.71
    depending
    -0.71
     conscientious
    -0.70
     describ
    -0.69
     concerned
    -0.69
    POSITIVE LOGITS
     Orchestra
    1.12
     Presents
    1.10
     Collection
    1.01
     Club
    1.00
     Suite
    0.97
     Massacre
    0.96
     Begins
    0.92
     Workshop
    0.92
     Redux
    0.91
     Remastered
    0.91
    Activations Density 0.455%

    No Known Activations