INDEX

Explanations

references to low values or low measurements in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GOTREF

-0.86

 verksam

-0.83

 virtù

-0.78

 tekem

-0.77

++]=

-0.71

 esercit

-0.71

 engraçadas

-0.71

 AssemblyTitle

-0.70

FormTagHelper

-0.70

 arbres

-0.69

POSITIVE LOGITS

low

2.02

LOW

1.99

Low

1.97

Low

1.80

low

1.65

 lowest

1.54

 Lowry

1.50

低

1.50

LOW

1.49

 Lowest

1.42

Activations Density 0.084%

references to low values or low measurements in various contexts

No Comments

No Known Activations