INDEX

Explanations

proper nouns, particularly names and geographic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

MLLoader

-0.68

 NSCoder

-0.57

 ویکی‌پدی

-0.56

KommentareTeilen

-0.56

principalColumn

-0.55

RTEE

-0.54

expandindo

-0.53

 propOrder

-0.53

 disambiguazione

-0.53

MemoryWarning

-0.52

POSITIVE LOGITS

mann

0.77

MANN

0.56

 Bump

0.50

 Peel

0.46

ann

0.45

 damp

0.45

 Damp

0.44

 bang

0.44

uta

0.44

 inflation

0.44

Activations Density 0.494%

proper nouns, particularly names and geographic references

No Comments

No Known Activations