INDEX

Explanations

terms that indicate approximation or roughness

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

ola

-0.66

 klart

-0.58

TV

-0.57

 chaîne

-0.56

mela

-0.56

test

-0.55

cassert

-0.55

SuppressLint

-0.55

testa

-0.54

 useState

-0.54

POSITIVE LOGITS

 Rough

1.25

__*/

1.18

rough

1.16

Rough

1.15

 getRule

1.07

 approximations

1.06

 rough

1.05

 Approximate

1.05

NameInMap

1.04

 approximated

1.04

Activations Density 0.153%

terms that indicate approximation or roughness

No Comments

No Known Activations