© 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. 9958
    Prev
    Next
    INDEX
    Explanations

    phrases related to new discoveries, developments, or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and present tense verbs indicating states or conditions

    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
    inventoryQuantity
    -0.73
     declines
    -0.66
     grades
    -0.64
     refunds
    -0.62
     Errors
    -0.59
     IMAGES
    -0.58
     Convers
    -0.57
     Accuracy
    -0.57
     Forget
    -0.57
    âĨij
    -0.57
    POSITIVE LOGITS
     born
    1.04
     constructed
    1.03
     devised
    1.03
     formed
    1.02
     underway
    1.01
     created
    0.99
     emerging
    0.95
     erected
    0.93
     laun
    0.92
    found
    0.90
    Activations Density 0.209%

    No Known Activations