INDEX

Explanations

references to rankings, ties, and comparisons in competition or sports

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

"tie" or "tied"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

httphttps

-0.66

aarrggbb

-0.64

+:+

-0.63

 beginnetje

-0.60

yntaxException

-0.58

Gön

-0.58

stateProvider

-0.57

 CreateTagHelper

-0.57

ChildScrollView

-0.56

Cyfeiriadau

-0.56

POSITIVE LOGITS

tie

2.52

 tied

2.27

 ties

2.06

Tie

2.06

 tying

1.98

Tie

1.95

 Tied

1.84

 Ties

1.74

Tied

1.69

TIE

1.66

Activations Density 0.130%

references to rankings, ties, and comparisons in competition or sports

"tie" or "tied"

No Comments

No Known Activations