INDEX

Explanations

phrases related to programming errors and exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

rrggbb

-0.83

setViewportView

-0.82

 useRouter

-0.71

verket

-0.70

 vorn

-0.69

Marlene

-0.69

ibatis

-0.69

rgba

-0.67

icolor

-0.67

duğu

-0.64

POSITIVE LOGITS

 Exception

0.79

Exception

0.72

EXCEPTION

0.69

 exemption

0.69

SSE

0.65

 Kenner

0.64

 exception

0.62

 exciter

0.62

 Jérôme

0.59

SSE

0.59

Activations Density 0.044%

phrases related to programming errors and exceptions

No Comments

No Known Activations