INDEX

Explanations

phrases indicating uncertainty or conditionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 réguli

-0.83

 spørsmål

-0.76

 Blackman

-0.76

 végétale

-0.75

 culturelles

-0.73

antMatchers

-0.72

 énergé

-0.72

 anillos

-0.71

 Rangel

-0.70



-0.69

POSITIVE LOGITS

enumi

1.01

 have

0.91

 MainAxisSize

0.72

be

0.72

avía

0.64

 ProtoMessage

0.62

resizingMask

0.62

 mott

0.60

 spect

0.60

 Maynard

0.60

Activations Density 0.155%

phrases indicating uncertainty or conditionality

No Comments

No Known Activations