INDEX

Explanations

phrases related to self-reference and existential concepts

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

OGND

-0.95

NameInMap

-0.90

 Majefty

-0.84

Yud

-0.84

richTextPanel

-0.83

voorbeeld

-0.75

Geplaatst

-0.74

 actualité

-0.74

 Prist

-0.72

 виправивши

-0.69

POSITIVE LOGITS

se

1.02

 להת

0.93

 haberse

0.90

 sich

0.83

Se

0.82

Mc

0.75

'},

0.74

 се

0.74

się

0.73

'),

0.72

Activations Density 0.032%

phrases related to self-reference and existential concepts

No Comments

No Known Activations