INDEX

Explanations

words related to differing viewpoints or ways of seeing things

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

 NSCoder

-0.76

رشف

-0.75

RegistryLite

-0.73

 Walkover

-0.71

 Exacts

-0.69

Życiorys

-0.68

 propOrder

-0.67

adə

-0.65

HasAnnotation

-0.65

localized

-0.64

POSITIVE LOGITS

 view

2.19

 views

2.06

view

1.92

View

1.77

VIEW

1.71

 VIEW

1.67

views

1.65

 Views

1.65

 viewed

1.57

 VIEWS

1.47

Activations Density 0.087%

words related to differing viewpoints or ways of seeing things

No Comments

No Known Activations