INDEX

Explanations

mathematical or technical notation and terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

eadas

-0.46

Keeper

-0.45

nologies

-0.44

ENES

-0.43

 podio

-0.43

ATEUR

-0.42

 cont

-0.41

PERATURE

-0.41

keeper

-0.41

abar

-0.40

POSITIVE LOGITS

 linkovi

0.92

TestTools

0.89

 nakalista

0.85

 henvisninger

0.82

 שוליים

0.76

itinéraire

0.75

AnchorStyles

0.73

Abitanti

0.68

 Waray

0.68

Hentet

0.67

Activations Density 0.688%

mathematical or technical notation and terminology

No Comments

No Known Activations