INDEX

Explanations

terms related to execution and tracking processes or events in code or data

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adaptiveStyles

-0.67

ValueStyle

-0.63

contentLoaded

-0.62

LabelTagHelper

-0.58

MessageTagHelper

-0.53

addCriterion

-0.51

 defaultstate

-0.50

 Administrativna

-0.49

Lycka

-0.48

 ✭✭

-0.47

POSITIVE LOGITS

Run

0.65

documented

0.65

run

0.64

Runtime

0.64

 documented

0.62

 tracing

0.61

Run

0.61

 Tracing

0.60

Trace

0.59

 Trace

0.59

Activations Density 0.269%

terms related to execution and tracking processes or events in code or data

No Comments

No Known Activations