INDEX

Explanations

programming-related functions and methods

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

tagHelperRunner

-0.80

mergeFrom

-0.69

 fieldNum

-0.69

 protoimpl

-0.66

XtraReports

-0.66

 BoxFit

-0.65

GOTREF

-0.64

embatan

-0.64

principalColumn

-0.62

StructEnd

-0.61

POSITIVE LOGITS

openSession

0.58

 Falun

0.52

 BaseController

0.51

 Pharisees

0.50

 Waray

0.50

 mickey

0.49

 Bambi

0.49

 mContext

0.48

ObjectContext

0.47

AnimationsModule

0.47

Activations Density 0.096%

programming-related functions and methods

No Comments

No Known Activations