INDEX

Explanations

terms related to incidents involving violence and medical emergencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

PyExc

-0.78

KommentareTeilen

-0.72

RenderAtEndOf

-0.71

ConstraintMaker

-0.69

rrggbb

-0.68

 iprot

-0.68

 MenuView

-0.65

 المعيارى

-0.65

UnknownFields

-0.64

ToBounds

-0.64

POSITIVE LOGITS

 taken

0.64

 flown

0.61

 transported

0.60

 conscious

0.58

 consciente

0.57

air

0.57

 stabilized

0.56

 treated

0.55

Advertisement

0.51

 hospitalized

0.50

Activations Density 0.204%

terms related to incidents involving violence and medical emergencies

No Comments

No Known Activations