INDEX

Explanations

references to water coolers and related products.

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

mentions of the word "water."

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to water, especially when used as a noun at the beginning of a phrase or sentence.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ExecuteAsync

-0.79

WriteTagHelper

-0.67

ecap

-0.65

fromnode

-0.60

 >=",

-0.60

็จ

-0.60

SharedDtor

-0.60

Abp

-0.60

enterOuterAlt

-0.59

errHandler

-0.58

POSITIVE LOGITS

logged

0.65

oluble

0.59

tight

0.58

💦

0.57

 vapor

0.55

 Water

0.54

 vapour

0.54

💧

0.54

cress

0.53

Water

0.53

Activations Density 0.115%

references to water coolers and related products.

mentions of the word "water."

references to water, especially when used as a noun at the beginning of a phrase or sentence.

No Comments

No Known Activations