INDEX

Explanations

references to important metrics or dimensions related to data structures or physical attributes, with a focus on size and specific injuries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

:✨

-0.71

thâu

-0.70

chesse

-0.68

 BoxDecoration

-0.66

 createSlice

-0.63

 dubbed

-0.62

 ToString

-0.62

ceptre

-0.61

 groupBox

-0.61

urbation

-0.61

POSITIVE LOGITS

 knee

0.87

 knees

0.85

 Knee

0.73

knee

0.68

 contrary

0.55

 planted

0.54

 cray

0.53

 Handy

0.52

 Intelli

0.52

 investigator

0.51

Activations Density 0.046%

references to important metrics or dimensions related to data structures or physical attributes, with a focus on size and specific injuries

No Comments

No Known Activations