INDEX

Explanations

segments of text that contain numerical data or structured information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.70

,”

-0.66

Tazama

-0.66

-0.65

.\"

-0.64

السكان

-0.63

Enllaços

-0.63

 Etats

-0.62

WriteLiteral

-0.61

-0.60

POSITIVE LOGITS

ⓘ

0.66

<table>

0.65

<sup>

0.63

featureID

0.63

 NgModule

0.62

→

0.62

 holotype

0.62

†

0.62

←

0.60

</td>

0.59

Activations Density 0.332%

segments of text that contain numerical data or structured information

No Comments

No Known Activations