INDEX

Explanations

expressions of novelty or newness

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

 <<<<<<<<<<<<<<

-0.85

Autoritní

-0.72

 resourceCulture

-0.72

مصادر

-0.68

rungsseite

-0.64

 InputDecoration

-0.63

enumi

-0.63

цездатний

-0.62

erenc

-0.60

SequentialGroup

-0.59

POSITIVE LOGITS

 unfamiliar

0.73

ksom

0.64

 stranger

0.61

stranger

0.60

 ismer

0.60

 inconn

0.59

 desconhe

0.58

isNew

0.58

 novedad

0.57

 novel

0.55

Activations Density 0.155%

expressions of novelty or newness

No Comments

No Known Activations