INDEX

Explanations

phrases related to research and formal documentation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.65

 esternos

-0.64

rrggbb

-0.55

ScopeManager

-0.54

 ब्रेकडाउन

-0.53

 препратки

-0.52

 Alva

-0.51

 Magi

-0.49

นะนำ

-0.49

⎨

-0.49

POSITIVE LOGITS

mn

1.15

mn

0.65

mycompany

0.55

BCD

0.52

 Monteiro

0.51

zzleHttp

0.51

 comptes

0.50

RequestQueue

0.50

 coordinates

0.49

yelitis

0.49

Activations Density 0.263%

phrases related to research and formal documentation

No Comments

No Known Activations