INDEX

Explanations

references to individuals in authoritative positions and instances of fault or blame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

₤

-0.66

Hentet

-0.59

tvguidetime

-0.59

ciclopedia

-0.55

DataMember

-0.54

 بيها

-0.52

Ӏ

-0.52

 isles

-0.50

 Pais

-0.50

 كورة

-0.49

POSITIVE LOGITS

RenderAtEndOf

0.79

TintMode

0.68

Jereo

0.66

NOPQRST

0.64

 kont

0.62

 fault

0.62

 مشين

0.61

ArgumentParser

0.59

 faults

0.58

xFFFFFFFF

0.57

Activations Density 0.074%

references to individuals in authoritative positions and instances of fault or blame

No Comments

No Known Activations