INDEX

Explanations

discussions that involve clarifications and meanings related to statements or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TypedDataSet

-0.76

yntaxException

-0.71

 &___

-0.65

 يتيمه

-0.63

 nakalista

-0.62

 onCreate

-0.62

SPATH

-0.61

 Along

-0.60

 Winaray

-0.57

noinspection

-0.55

POSITIVE LOGITS

maksud

0.67

 chodzi

0.66

 meaning

0.62

 mean

0.60

 intende

0.60

 maksud

0.59

 منظور

0.59

 bedoeld

0.57

 meant

0.56

什么意思

0.55

Activations Density 0.221%

discussions that involve clarifications and meanings related to statements or concepts

No Comments

No Known Activations