© 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. 3-RES-JB
    11. 22642
    Prev
    Next
    INDEX
    Explanations

    specific organizations or locations mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of entertainment companies or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lying
    -0.88
    */(
    -0.87
    ggies
    -0.81
    orders
    -0.78
    lies
    -0.77
    tons
    -0.77
    date
    -0.76
    making
    -0.75
    ãĥĥãĥĪ
    -0.74
    maker
    -0.73
    POSITIVE LOGITS
    ICAN
    1.05
     AMC
    0.94
     suspic
    0.89
     Studios
    0.85
     mosqu
    0.76
     studios
    0.73
     Cran
    0.72
    URA
    0.71
    illo
    0.71
     Networks
    0.70
    Activations Density 0.010%

    No Known Activations