INDEX

Explanations

instances of the word "es."

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

BoxShadow

-0.84

ագրություններ

-0.81

LikeLike

-0.78

HtmlAttribute

-0.74

 Normandie

-0.72

ThroughAttribute

-0.71

IntegerField

-0.70

 đương

-0.69

ulihan

-0.67

moh

-0.66

POSITIVE LOGITS

Es

1.91

Es

1.82

es

1.82

ES

1.60

ES

1.49

es

1.49

 Estelle

1.32

 Esmeralda

1.21

 Esch

1.20

 Esposito

1.15

Activations Density 0.071%

instances of the word "es."

No Comments

No Known Activations