INDEX

Explanations

actions involving dipping or soaking items, particularly in cooking or food preparation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CodeAttribute

-0.72

EDEFAULT

-0.72

createTextNode

-0.67

 AssemblyCulture

-0.66

뀐

-0.66

drawSprites

-0.66

ArgsConstructor

-0.63

principalColumn

-0.62

IndentedString

-0.62

GeneratedValue

-0.62

POSITIVE LOGITS

 dipping

1.05

 soaking

1.05

 soak

1.02

 dipped

1.02

 soaked

1.01

 immerse

0.96

 immersion

0.96

 immersed

0.95

dip

0.93

 Immersion

0.92

Activations Density 0.721%

actions involving dipping or soaking items, particularly in cooking or food preparation

No Comments

No Known Activations