INDEX

Explanations

negations or refusals indicated by "not" and "isn't"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 cartes

-0.64

 Data

-0.61

zku

-0.61

誼

-0.60

 cards

-0.58

OPC

-0.58

Advertisements

-0.57

atlas

-0.57

OP

-0.57

are

-0.56

POSITIVE LOGITS

"])

1.15

ьаж

1.10

AddTagHelper

1.06

theless

1.04

'))

0.97

tonsoft

0.95

)}</

0.94

 useAppContext

0.92

PerformLayout

0.89

 CommonModule

0.89

Activations Density 0.091%

negations or refusals indicated by "not" and "isn't"

No Comments

No Known Activations