INDEX

Explanations

expressions indicating strong opinions or recommendations

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

-0.79

IsMutable

-0.61

UserScript

-0.61

TargetException

-0.58

InteropServices

-0.57

醐

-0.56

Viitteet

-0.56

Rujukan

-0.55

ogn

-0.54

ayage

-0.53

POSITIVE LOGITS

jsii

0.61

KURZBESCHREIBUNG

0.56

trino

0.53

:][

0.52

 démocr

0.51

autorest

0.51

mnop

0.49

 zobac

0.47

 interdit

0.47

 wiem

0.47

Activations Density 0.009%

expressions indicating strong opinions or recommendations

No Comments

No Known Activations