INDEX

Explanations

interrogative phrases or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

akos

-0.61

 Schur

-0.59

nao

-0.59

 Aristi

-0.59

 Blatt

-0.59

 Rudi

-0.58

 itſelf

-0.57

Xna

-0.56

nash

-0.56

ſelf

-0.56

POSITIVE LOGITS

qu

1.02

IsMutable

0.86

 تضيفلها

0.82

 שוליים

0.79

 bahawa

0.79

 WHETHER

0.74

que

0.73

Gdy

0.72

AccessorTable

0.70

]")]

0.70

Activations Density 0.055%

interrogative phrases or expressions

No Comments

No Known Activations