INDEX

Explanations

location names and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 itſelf

-0.81

neurial

-0.77

 themſelves

-0.76

Efq

-0.73

theless

-0.68

 CHAPITRE

-0.68

 myſelf

-0.67

culares

-0.67

 auffi

-0.67

cursions

-0.66

POSITIVE LOGITS

WindowConstants

0.55

SourceChecksum

0.48

 كورة

0.43

 CanadaChoose

0.42

ện

0.41

TypedDataSet

0.41

 Latimer

0.40

DIV

0.40

Sal

0.38

 Federal

0.38

Activations Density 0.099%

location names and addresses

No Comments

No Known Activations