INDEX

Explanations

terms related to legal procedures and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

IsContent

-0.73

AndEndTag

-0.73

URLException

-0.72

 الحره

-0.69

SourceChecksum

-0.65

 pinulongan

-0.63

SPATH

-0.63

CloseOperation

-0.62

CppMethod

-0.62

évaluateur

-0.62

POSITIVE LOGITS

 unnecessary

2.05

 useless

1.96

 waste

1.88

 pointless

1.81

 superfluous

1.81

 inutile

1.77

 inneces

1.75

 redundant

1.68

useless

1.67

waste

1.65

Activations Density 0.516%

terms related to legal procedures and decisions

No Comments

No Known Activations