INDEX

Explanations

phrases indicating personal achievement or recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

LookAnd

-0.49

gis

-0.46

CodeAnalysis

-0.45

IUrlHelper

-0.44

dismiss

-0.43

蔵

-0.43

度に

-0.42

意外

-0.41

WebElementEntity

-0.41

AspectRatio

-0.41

POSITIVE LOGITS

tvguidetime

0.92

 myſelf

0.84

establishing

0.81

 Establishing

0.78

 himſelf

0.77

established

0.77

 foothold

0.75

 itſelf

0.74

 themſelves

0.74

 Established

0.74

Activations Density 0.210%

phrases indicating personal achievement or recognition

No Comments

No Known Activations