INDEX

Explanations

numerical values and time references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 pops

-0.58

σθαι

-0.57

 self

-0.57

 وتسجيلات

-0.55

tvguidetime

-0.53

Související

-0.53

Rptr

-0.50

 fires

-0.49

ſelf

-0.49

windowFixed

-0.48

POSITIVE LOGITS

tagHelperRunner

0.73

rungsseite

0.64

SceneManagement

0.60

0.56

 BoxFit

0.55

DataAdapter

0.55

InvalidProtocol

0.54

 AssemblyVersion

0.52

}{*}{

0.51

CodeDom

0.49

Activations Density 0.166%

numerical values and time references

No Comments

No Known Activations