INDEX

Explanations

emotionally charged terms and expressions of personal experiences

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

in

-0.88

تقاوى

-0.70

aining

-0.66

 inti

-0.66

inals

-0.64

ining

-0.64

in

-0.63

ing

-0.62

line

-0.61

principalColumn

-0.61

POSITIVE LOGITS

cutt

0.71

aga

0.63

 certa

0.61

 comb

0.61

 rema

0.58

 surpris

0.58

beg

0.58

mak

0.57

 expla

0.56

liv

0.56

Activations Density 0.107%

emotionally charged terms and expressions of personal experiences

No Comments

No Known Activations