INDEX

Explanations

references to historical subjects and discussions

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

ConstraintMaker

-0.77

addPreferredGap

-0.76

 ſmall

-0.75

 Shakspeare

-0.73

AccessorTable

-0.72

 rigue

-0.71

 Lombar

-0.71

 testSet

-0.71

 Vaticano

-0.71

 greateſt

-0.70

POSITIVE LOGITS

 history

2.59

history

2.21

 History

2.15

 histories

2.02

History

1.97

 HISTORY

1.94

HISTORY

1.83

 useHistory

1.60

 historia

1.58

 Histories

1.54

Activations Density 0.067%

references to historical subjects and discussions

No Comments

No Known Activations