© 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. 10-RES-JB
    11. 6970
    Prev
    Next
    INDEX
    Explanations

    specific monetary values in US dollars

    oai_token-act-pair · gpt-3.5-turbo

    key terms and entities related to various systems and contexts, such as campaigns, media formats, and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.67
    leon
    -0.63
    for
    -0.63
    llah
    -0.63
    slow
    -0.60
    lves
    -0.57
     Cheong
    -0.57
    assian
    -0.57
    inventoryQuantity
    -0.57
    vez
    -0.57
    POSITIVE LOGITS
     purposes
    1.86
     sake
    1.71
    ummies
    1.09
     purpose
    1.04
     reasons
    1.02
     lovers
    0.84
     reason
    0.80
     upcoming
    0.78
     beginners
    0.76
     duration
    0.75
    Activations Density 0.632%

    No Known Activations