INDEX

Explanations

word patterns related to subjective experiences and emotional reactions

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

VIAF

-0.72

uxxxx

-0.63

}{*}{

-0.62

RegressionTest

-0.60

 CrossRef

-0.58

 Töchter

-0.57

ⓧ

-0.56

webElementXpaths

-0.55

udert

-0.55

Pyx

-0.55

POSITIVE LOGITS

 whatsoever

1.86

 affatto

1.18

at

1.08

 כלל

0.98

 alls

0.95

AT

0.88

soever

0.85

 vůbec

0.84

 whatever

0.78

 вообще

0.77

Activations Density 0.189%

word patterns related to subjective experiences and emotional reactions

No Comments

No Known Activations