INDEX

Explanations

the word "That" and its various contexts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Schlu

-0.59

########.

-0.58

esticular

-0.55

ASX

-0.55

 Alford

-0.55

 tyres

-0.54

océan

-0.53

Ỏ

-0.53

 admiten

-0.53

ünkü

-0.52

POSITIVE LOGITS

That

0.81

 Chwiliwch

0.78

 That

0.71

writeFieldEnd

0.62

ThroughAttribute

0.61

'{@

0.61

 therein

0.60

"},

0.59

 مرئيه

0.59

ARE

0.59

Activations Density 0.119%

the word "That" and its various contexts in the text

No Comments

No Known Activations