INDEX

Explanations

sections of the text marked by high activation values, indicating potential code or programming-related content

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

 ―――――

-1.04

Portail

-0.94



-0.93

Efq

-0.89

mybatisplus

-0.87

ChildScrollView

-0.85

 cdti

-0.82

CWE

-0.82

 Dara

-0.82

 Theſe

-0.81

POSITIVE LOGITS

1.72

1.21

1.17

1.14

1.12

1.09

0.99

0.98

0.97

Activations Density 0.142%

sections of the text marked by high activation values, indicating potential code or programming-related content

No Comments

No Known Activations