INDEX

Explanations

instances of the word "description" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyProduct

-0.87

SourceChecksum

-0.72

expandindo

-0.63

انيف

-0.59

prnewswire

-0.59

ClientRect

-0.57

CompilerServices

-0.56

JNIEnv

-0.55

EndInit

-0.55

thenReturn

-0.55

POSITIVE LOGITS

 description

3.47

 descriptions

3.05

description

2.79

 Description

2.74

 DESCRIPTION

2.63

Description

2.63

 describe

2.55

 Descriptions

2.51

 describing

2.49

descriptions

2.44

Activations Density 0.152%

instances of the word "description" and related terms

No Comments

No Known Activations