INDEX

Explanations

verbs and actions related to understanding, analysis, and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

IgA

-0.52

 HasFactory

-0.49

 hypotension

-0.49

 EGFR

-0.49

 Poincaré

-0.49

 Dalai

-0.48

IgE

-0.47

 Poincar

-0.47

 você

-0.47

 maxn

-0.46

POSITIVE LOGITS

the

1.42

1.09

an

0.96

 some

0.90

 their

0.88

ngthen

0.82

ulate

0.82

++

0.82

 those

0.81

[]

0.80

Activations Density 2.793%

verbs and actions related to understanding, analysis, and improvement

No Comments

No Known Activations