INDEX

Explanations

phrases that indicate the presence of detailed descriptions or specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 myſelf

-0.74

IsContent

-0.73

 themſelves

-0.67

 cauſe

-0.67

 الاطلاع

-0.67

reportWebVitals

-0.65

RenderAtEndOf

-0.62

 houſe

-0.62

 himſelf

-0.61

 Italij

-0.61

POSITIVE LOGITS

no

0.72

 CURIAM

0.71

RunWith

0.64

with

0.62

 featuring

0.60

holds

0.59

 with

0.58

JsonInclude

0.57

OwnProperty

0.56

 containing

0.56

Activations Density 0.388%

phrases that indicate the presence of detailed descriptions or specifications

No Comments

No Known Activations