INDEX

Explanations

references to names and places, especially those associated with "Wa" or "Ka."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 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

Not in Any Lists

No Comments

Negative Logits

StoryboardSegue

-0.66

 arşivlendi

-0.63

 незавершена

-0.57

に

-0.55

hara

-0.55

cé

-0.55

Portail

-0.53

StringTokenizer

-0.53

ScopeManager

-0.52

Välislingid

-0.51

POSITIVE LOGITS

thesis

0.49

ver

0.47

ษา

0.47

wapV

0.46

copg

0.45

tenor

0.44

square

0.44

 dieux

0.44

 hendes

0.44

 Ostat

0.44

Activations Density 0.259%

references to names and places, especially those associated with "Wa" or "Ka."

No Comments

No Known Activations