INDEX

Explanations

assertion statements used in testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Montal

-0.91

 Audiodateien

-0.82

 maxn

-0.71

eam

-0.70

EMBLY

-0.66

wet

-0.64

onnaissance

-0.63

bè

-0.61

imler

-0.61

?>>

-0.60

POSITIVE LOGITS

assert

2.23

 assert

1.63

cassert

1.56

 asserts

1.31

 asserted

1.19

 asserting

1.18

 assertions

1.11

 Assertion

0.98

 claims

0.97

 assertion

0.92

Activations Density 0.038%

assertion statements used in testing

No Comments

No Known Activations