INDEX

Explanations

various forms of the word "that" as well as related pronouns like "who" and "whose."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 урна

-0.57

rinology

-0.51

,"\

-0.50

HasBeenSet

-0.49

دانشنامهٔ

-0.48

us

-0.47

痺

-0.47

 eventualmente

-0.47

itively

-0.46

Einzelnachweise

-0.46

POSITIVE LOGITS

AndEndTag

0.83

 MonoBehaviour

0.74

AnchorStyles

0.67

VideoCapture

0.67

AddTagHelper

0.66

ChildScrollView

0.66

 '\\;'

0.64

Portale

0.64

npos

0.62

 bParam

0.59

Activations Density 0.253%

various forms of the word "that" as well as related pronouns like "who" and "whose."

No Known Activations