INDEX

Explanations

the repeated use of the word "had"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ValueStyle

-0.90

LLocation

-0.88

AndEndTag

-0.84

ItemBackground

-0.76

 actualidad

-0.74

PreferredItem

-0.74

Искәрмәләр

-0.73

woordig

-0.73

ChildScrollView

-0.73

GraphicsUnit

-0.72

POSITIVE LOGITS

 hoped

1.25

 originally

1.12

 previously

1.09

 earlier

1.05

 originalmente

0.95

 ursprünglich

0.93

 initially

0.88

Earlier

0.87

previously

0.84

 planned

0.80

Activations Density 0.132%

the repeated use of the word "had"

No Comments

No Known Activations