INDEX

Explanations

statements related to the state or condition of entities, particularly those using the verb "is."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 purpoſe

-0.94

 houſe

-0.92

 Chriftian

-0.90

 Jefus

-0.89

 ſeveral

-0.88

 Monfieur

-0.88

 Majefty

-0.88

脚注の使い方

-0.87

Efq

-0.87

 pleaſure

-0.86

POSITIVE LOGITS

is

0.70

XmlAccessType

0.60

 will

0.57

was

0.55

has

0.51

not

0.51

may

0.50

 also

0.49

ädie

0.48

can

0.47

Activations Density 0.786%

statements related to the state or condition of entities, particularly those using the verb "is."

No Comments

No Known Activations