© 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. 9313
    Prev
    Next
    INDEX
    Explanations

    descriptions or reviews of different types of movies or literary works

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of film genres and their characteristics, particularly focusing on gritty or artistic elements

    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
     ESV
    -0.82
    ospons
    -0.80
    rade
    -0.78
    çİĭ
    -0.77
    ANA
    -0.76
    chuk
    -0.76
    --+
    -0.76
    ername
    -0.75
     Allaah
    -0.75
     Marketable
    -0.74
    POSITIVE LOGITS
     protagonists
    1.33
     suspense
    1.27
     satire
    1.26
     gore
    1.25
     thriller
    1.24
     protagonist
    1.23
     satir
    1.20
     dystopian
    1.20
     Kubrick
    1.18
     themes
    1.18
    Activations Density 0.391%

    No Known Activations