INDEX

Explanations

data entries or indicators related to specific statistics or numerical information

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

pattern indicators in structured data representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-1.03

tagHelperRunner

-0.79

ValueStyle

-0.66

jspb

-0.62

 strconv

-0.61

 unknownFields

-0.60

agaimana

-0.60



-0.60

CppMethod

-0.59

migrationBuilder

-0.58

POSITIVE LOGITS

</em>

0.85

</i>

0.74

0.70

,”

0.63

!”

0.61

,"

0.60

.”

0.59

”

0.59

!"

0.58

Activations Density 0.300%

data entries or indicators related to specific statistics or numerical information

pattern indicators in structured data representations

No Comments

No Known Activations