INDEX

Explanations

references to specific individuals and their roles in television or film

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

+#+

-0.77

TagMode

-0.61

 ComVisible

-0.50

SaveChangesAsync

-0.49

wikia

-0.48

setupUi

-0.48

chism

-0.47

тності

-0.47

 AspNetCore

-0.47

matlab

-0.47

POSITIVE LOGITS

 Vietnam

0.82

 hippie

0.80

Vietnam

0.72

 vietnam

0.66

 Woodstock

0.65

انيف

0.65

 communes

0.64

 psychedelic

0.63

 chng

0.60

Unicorn

0.59

Activations Density 0.393%

references to specific individuals and their roles in television or film

No Comments

No Known Activations