INDEX

Explanations

references to ice and ice-related products

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

NamedQueries

-0.97

 -->>

-0.94

BibitemShut

-0.93

 myſelf

-0.93

@"/

-0.91

 itſelf

-0.91

 themſelves

-0.89

theless

-0.88

StoryboardSegue

-0.87

soever

-0.87

POSITIVE LOGITS

ice

2.26

Ice

2.15

Ice

1.97

ICE

1.88

ice

1.64

ICE

1.42

 hielo

1.26

冰

1.18

 iced

1.13

Eis

1.13

Activations Density 0.051%

references to ice and ice-related products

No Comments

No Known Activations