INDEX

Explanations

references to specific seasons in various contexts, particularly in relation to narratives or events

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Middle

-0.52

Middle

-0.48

 French

-0.48

 white

-0.47

 middle

-0.46

 White

-0.46

white

-0.46

 West

-0.45

 Cartwright

-0.45

 Hart

-0.44

POSITIVE LOGITS

SceneManagement

0.88

 SEASON

0.86

season

0.82

 season

0.81

Season

0.81

 Season

0.79

seasons

0.79

SEASON

0.77

IsMutable

0.76

 Seasons

0.74

Activations Density 0.150%

references to specific seasons in various contexts, particularly in relation to narratives or events

No Known Activations