INDEX

Explanations

characters and entities related to storytelling and narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

istoitu

-0.95

EDEFAULT

-0.94

parsedMessage

-0.88

 tartalomajánló

-0.88

featureID

-0.88

Personensuche

-0.87

 Мексичка

-0.87

setVerticalGroup

-0.85

yntaxException

-0.82

 ujednoznacz

-0.81

POSITIVE LOGITS

®,

0.51

('');

0.47

®

0.44

0.43

̈

0.41

жи

0.40

and

0.40

us

0.39

Activations Density 1.371%

characters and entities related to storytelling and narratives

No Comments

No Known Activations