INDEX

Explanations

phrases related to maximizing performance or efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

lappe

-0.60

 betweenstory

-0.57

IndentedString

-0.52

 repuesto

-0.50

 '\\;'

-0.48

Postup

-0.48

kew

-0.47

 cough

-0.47

InputTagHelper

-0.45

Easy

-0.45

POSITIVE LOGITS

 maximize

1.17

 maximizing

1.10

 maximizes

1.04

 maximized

1.01

maximize

0.97

 Maximize

0.96

 maximise

0.96

 optimize

0.95

 optimum

0.94

 optimal

0.92

Activations Density 0.492%

phrases related to maximizing performance or efficiency

No Comments

No Known Activations