INDEX

Explanations

proper nouns, particularly names and titles

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

 faſt

-0.69

 erop

-0.65

 againſt

-0.65

 itſelf

-0.64

 iſt

-0.63

↵↵

-0.63

 uſe

-0.62

 preſent

-0.61

 abstracta

-0.60

 myſelf

-0.60

POSITIVE LOGITS

1.08

 getM

1.00

setH

0.99

 getB

0.98

0.97

0.96

 getP

0.96

0.94

Activations Density 0.859%

proper nouns, particularly names and titles

No Comments

No Known Activations