INDEX

Explanations

instances of navigation-related elements and structure in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 itſelf

-0.72

 تضيفلها

-0.69

:].

-0.69

 grunn

-0.65

 supérieures

-0.64

 purpoſe

-0.64

Vle

-0.63

 sexes

-0.62

 Houſe

-0.62

 myſelf

-0.61

POSITIVE LOGITS

context

1.07

Context

0.89

ctx

0.87

ctx

0.85

getContext

0.85

ى

0.78

CONTEXT

0.75

 away

0.75

contexts

0.67

Nav

0.65

Activations Density 0.079%

instances of navigation-related elements and structure in the document

No Comments

No Known Activations