© 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. 6-RES-JB
    11. 18448
    Prev
    Next
    INDEX
    Explanations

    phrases related to programs or initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or organizational programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLASSIFIED
    -0.72
     dilig
    -0.71
    pick
    -0.69
     humidity
    -0.67
    picking
    -0.64
     IMAGES
    -0.64
    xious
    -0.63
    ModLoader
    -0.63
    ãĥ´
    -0.62
    Boss
    -0.61
    POSITIVE LOGITS
    mable
    1.75
    matic
    1.43
    matically
    1.42
    mers
    0.94
     Gutenberg
    0.88
     instituted
    0.85
    atically
    0.82
    atical
    0.81
    mes
    0.81
    eers
    0.80
    Activations Density 0.035%

    No Known Activations