INDEX

Explanations

expressions and concepts related to fear and anxiety

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

"fear"

np_acts-logits-general · gemini-2.0-flash

fear, fear not, fear of, fearlessness

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 متعلقه

-1.07

 ivelany

-0.97

AccessorTable

-0.90

 '\\;'

-0.88

naires

-0.88

 يتيمه

-0.86

 EconPapers

-0.83

 HttpNotFound

-0.83

Tikang

-0.82

 المعيارى

-0.81

POSITIVE LOGITS

er

0.98

ER

0.66

rrrrrr

0.61

rrr

0.60

rrrrr

0.58

0.55

rr

0.54

rs

0.54

Ier

0.53

 paire

0.53

Activations Density 0.174%

expressions and concepts related to fear and anxiety

"fear"

fear, fear not, fear of, fearlessness

No Comments

No Known Activations