INDEX

Explanations

phrases that indicate duration or time-related references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ConstraintMaker

-1.03

 eventdata

-0.91

 AssemblyVersion

-0.90

 lenker

-0.88

 Roskov

-0.88

mybatisplus

-0.87

MigrationBuilder

-0.86

jspx

-0.84

ngdoc

-0.83

 MessageBoxIcon

-0.82

POSITIVE LOGITS

For

1.17

For

1.10

FOR

0.82

FOR

0.81

for

0.78

for

0.70

 Для

0.67

Для

0.61

 purposes

0.60

To

0.59

Activations Density 0.112%

phrases that indicate duration or time-related references

No Comments

No Known Activations