INDEX

Explanations

phrases related to coding, debugging, and technical issues

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

RenderAtEndOf

-0.86

MessageTagHelper

-0.83

 مشين

-0.75

 occaf

-0.72

ControllerAdvice

-0.71

AndEndTag

-0.71

 protoimpl

-0.70

Hauptartikel

-0.69

 <<<<<<<<<<<<<<

-0.65

viewDidLoad

-0.64

POSITIVE LOGITS

 without

1.35

without

1.17

 Without

1.14

Without

1.09

 reliably

1.01

 zonder

0.99

 ilman

0.97

 correctement

0.96

 adequately

0.96

 properly

0.93

Activations Density 0.690%

phrases related to coding, debugging, and technical issues

No Comments

No Known Activations