INDEX

Explanations

prepositions and their associated phrases

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

 take

-0.61

She

-0.56

im

-0.56

 indeed

-0.54

-0.53

 clearly

-0.53

 check

-0.53

 give

-0.53

put

-0.53

POSITIVE LOGITS

ymce

1.00

IUrlHelper

0.92

Personensuche

0.86

Rüyada

0.81

 مرئيه

0.78

addPreferredGap

0.78

IndentedString

0.77

 للمعارف

0.77

 spalle

0.76

Tikang

0.76

Activations Density 0.375%

prepositions and their associated phrases

No Comments

No Known Activations