INDEX

Explanations

words and phrases indicating emotional states or the presence of community interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

riso

-0.55

yntaxException

-0.50

Vidite

-0.49

 Brist

-0.48

rophes

-0.47

 rasg

-0.47

ungal

-0.47

ANGA

-0.47

ruch

-0.47

nesc

-0.46

POSITIVE LOGITS

 subsided

1.01

 subside

0.99

 abate

0.92

 dissip

0.84

 calmed

0.83

 calms

0.82

 tapering

0.81

 subs

0.80

 rece

0.80

 tapered

0.80

Activations Density 0.440%

words and phrases indicating emotional states or the presence of community interactions

No Comments

No Known Activations