INDEX

Explanations

connections between concepts and their impacts

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.60

vible

-0.58

-0.52

 revanche

-0.52

strophic

-0.50

kelijk

-0.50

ontale

-0.47

Specifiche

-0.46

曖昧さ回避

-0.43

gelegen

-0.43

POSITIVE LOGITS

 combined

2.66

 coupled

2.57

combined

2.23

 paired

2.16

 Coupled

2.10

 Combined

2.09

 combinado

2.00

 accompanied

1.98

Combined

1.97

coupled

1.97

Activations Density 1.071%

connections between concepts and their impacts

No Comments

No Known Activations