INDEX

Explanations

method declarations in code

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

 Monfieur

-0.84

 ſche

-0.80

 perſon

-0.78

 Diſ

-0.78

 himſelf

-0.78

 Jefus

-0.77

 houſe

-0.77

 pector

-0.76

 purpoſe

-0.75

 ſtre

-0.75

POSITIVE LOGITS

 void

2.61

void

2.20

Void

1.78

 VOID

1.70

VOID

1.68

 Void

1.59

 voids

1.58

})}

0.86

def

0.86

ruptedException

0.85

Activations Density 0.019%

method declarations in code

No Comments

No Known Activations