INDEX

Explanations

instances of the word "joining" and its variations, indicating a focus on inclusion or involvement

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

 itſelf

-0.72

 Persson

-0.66

lüssel

-0.60

NUMX

-0.60

 ſche

-0.59

ölcs

-0.56

tichetta

-0.55

ReusableCell

-0.55

 المكتبه

-0.54

POSITIVE LOGITS

 joins

0.86

 joining

0.81

Joining

0.81

 Joins

0.80

 Joining

0.77

DeleteBehavior

0.77

joins

0.76

 join

0.73

joining

0.68

AddTagHelper

0.65

Activations Density 0.135%

instances of the word "joining" and its variations, indicating a focus on inclusion or involvement

No Comments

No Known Activations