INDEX

Explanations

elements related to array shapes and indices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 مرئيه

-0.67

windowFixed

-0.63

Története

-0.62

PMailer

-0.58

 GenerationType

-0.58

 poveznice

-0.54

 Stä

-0.53

éről

-0.52

 صوتيه

-0.51

 ostavi

-0.51

POSITIVE LOGITS

+#+#

0.98

 CYTHON

0.74

")[

0.64

')[

0.63

")[

0.61

rifugal

0.60

 ImportError

0.59

rawDesc

0.58

')[

0.58

%>%

0.58

Activations Density 0.075%

elements related to array shapes and indices

No Comments

No Known Activations