INDEX

Explanations

instances of the word "jump" and its variations in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.54

if

-0.52

est

-0.51

-0.50

doras

-0.50

—

-0.49

 وهو

-0.48

tem

-0.48

text

-0.47

POSITIVE LOGITS

parsedMessage

1.35

:✨

1.06

Портал

1.05

 kasarigan

1.00

 ExecuteAsync

0.97

transQ

0.95

contentLoaded

0.94

InitVars

0.93

BufferException

0.92

 ProtoMessage

0.91

Activations Density 0.116%

instances of the word "jump" and its variations in various contexts

No Comments

No Known Activations