Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 269
    Prev
    Next
    INDEX
    Explanations

    terms related to open-source software, such as "OSS" and "Project Corvette"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific locations or events

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

    No Comments

    Negative Logits
    aneous
    -0.86
    inder
    -0.71
     Kend
    -0.70
    ulous
    -0.68
    ãĥ¡
    -0.68
     dent
    -0.67
    ples
    -0.65
    rell
    -0.64
     Dw
    -0.63
     Pax
    -0.63
    POSITIVE LOGITS
    sein
    0.91
    manship
    0.90
    eous
    0.84
    ynthesis
    0.82
    erness
    0.80
    geist
    0.78
    iness
    0.78
    FactoryReloaded
    0.74
    folios
    0.72
    yssey
    0.72
    Activations Density 0.036%

    No Known Activations