INDEX

Explanations

actions or processes that condense or summarize information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RefNanny

-0.60

 ویکی‌پدیا

-0.55

OCA

-0.53

 iprot

-0.53

Triggers

-0.52

 Buka

-0.52

hängen

-0.51

既

-0.51

gnus

-0.51

HttpPut

-0.51

POSITIVE LOGITS

 condensed

1.01

 condense

1.00

 condensing

0.92

 simplification

0.88

 distilled

0.87

 consolidation

0.85

 narrowed

0.83

 consolidating

0.82

 reduced

0.82

 reduction

0.82

Activations Density 0.606%

actions or processes that condense or summarize information

No Comments

No Known Activations