INDEX

Explanations

phrases indicating condition or comparison

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

hs

-0.45

}{$\

-0.43

react

-0.43

si

-0.41

trans

-0.41

也不能

-0.41

 Lawson

-0.41

 mesure

-0.41

mpia

-0.40

andır

-0.40

POSITIVE LOGITS

 חיצוניים

0.91

无论是

0.80

IntoConstraints

0.77

不管是

0.76

 passim

0.74

 both

0.73

 CreateTagHelper

0.73

saraba

0.71

 zarówno

0.71

ISupport

0.71

Activations Density 0.245%

phrases indicating condition or comparison

No Comments

No Known Activations