INDEX

Explanations

instances of the term "ho" and its variations, likely signaling emphasis or repetition in context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 مشين

-0.91

发表于

-0.90

 itſelf

-0.83

 ſeveral

-0.79

InitVars

-0.79

 ferons

-0.78

 purpoſe

-0.76

amaño

-0.75

 ſtate

-0.74

 ſte

-0.74

POSITIVE LOGITS

 through

0.95

ho

0.81

Ho

0.74

ho

0.69

 Through

0.67

Ho

0.66

HO

0.66

Through

0.65

 través

0.61

through

0.60

Activations Density 0.163%

instances of the term "ho" and its variations, likely signaling emphasis or repetition in context

No Comments

No Known Activations