INDEX

Explanations

phrases related to location or existence in context

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

endphp

-0.97

 AssemblyProduct

-0.85

 tartalomajánló

-0.79

UnusedPrivate

-0.75

]")]

-0.74

Välislingid

-0.72

TagMode

-0.72

ngdoc

-0.71

parsedMessage

-0.70

homonymie

-0.70

POSITIVE LOGITS

在

1.19

在

1.10

的在

1.08

在大

1.00

也在

0.89

在这

0.88

是在

0.86

於

0.85

就是在

0.85

在下

0.84

Activations Density 0.028%

phrases related to location or existence in context

No Comments

No Known Activations