INDEX

Explanations

phrases related to ongoing actions or processes

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

kosh

-0.77

gdx

-0.75

dersfield

-0.74

Mes

-0.73

auri

-0.72

insic

-0.70

 ModelExpression

-0.70

&__

-0.69

 поводу

-0.69

Xiaomi

-0.69

POSITIVE LOGITS

 continue

1.88

 continues

1.88

 continued

1.83

 Continue

1.80

 continuing

1.79

 Continues

1.74

 continuation

1.72

continues

1.68

continue

1.61

 Continuing

1.60

Activations Density 0.078%

phrases related to ongoing actions or processes

No Comments

No Known Activations