© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17020
    Prev
    Next
    INDEX
    Explanations

    verbs related to creation or establishment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "formed" and related variations, indicating creation or establishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Price
    -0.67
    crit
    -0.64
     pric
    -0.63
     downgrade
    -0.62
     Norton
    -0.60
    ignore
    -0.59
    price
    -0.57
    >>>>>>>>
    -0.57
     tom
    -0.56
     Handler
    -0.56
    POSITIVE LOGITS
     formed
    3.45
     forming
    2.04
     founded
    1.82
    formed
    1.75
     comprised
    1.65
     formation
    1.64
     constituted
    1.54
     disbanded
    1.53
     hatched
    1.52
     created
    1.48
    Activations Density 0.019%

    No Known Activations