INDEX

Explanations

symbols or characters used for greater-than comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

son

-0.59

ation

-0.57

istic

-0.53

-0.52

лю

-0.48

ate

-0.48

the

-0.47

Lo

-0.46

XtraGrid

-0.45

POSITIVE LOGITS

>>>>>>>>

1.31

>>>>>>>

1.23

>>>>

1.22

>>>>>>

1.22

>>>

1.11

displayquote

1.10

.>

1.10

}>\

1.07

_<

1.05

_>

1.05

Activations Density 0.255%

symbols or characters used for greater-than comparisons

No Comments

No Known Activations