INDEX

Explanations

terms related to allegations and legal claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Spoljašnje

-0.82

marvin

-0.76

or

-0.68

intr

-0.67

!("{

-0.66

 Castell

-0.64

{\

-0.64

TR

-0.64

IN

-0.63

Deacti

-0.63

POSITIVE LOGITS

 Jonny

0.93

CompilerServices

0.84

req

0.82

numerusform

0.82

AddTagHelper

0.82

︎

0.81

idx

0.80

 useCallback

0.80

ItemSelected

0.78

ViewFeatures

0.77

Activations Density 0.191%

terms related to allegations and legal claims

No Comments

No Known Activations