INDEX

Explanations

references to "super" or "supercharged" concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 kaynağından

-0.92

Geplaatst

-0.87

LEncoder

-0.86

 ModelExpression

-0.85

@[+][

-0.85

 intptr

-0.84

ScopeManager

-0.82

Vidite

-0.81

garmin

-0.78

RenderAtEndOf

-0.74

POSITIVE LOGITS

 super

3.19

Super

3.16

 Super

3.13

super

2.99

 SUPER

2.89

SUPER

2.68

 супер

2.27

 supers

2.13

超级

2.07

 Supers

2.05

Activations Density 0.087%

references to "super" or "supercharged" concepts

No Comments

No Known Activations