INDEX

Explanations

important organizations, institutions, or entities within a context

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

Preceding a location, company, or brand name

np_acts-logits-general · gemini-2.0-flash

company and brand names

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.56

URLException

-0.54

 generally

-0.51

 prior

-0.51

too

-0.49

 more

-0.49

the

-0.49

is

-0.48

 their

-0.47

POSITIVE LOGITS

 Houſe

0.85

 Chriftian

0.80

awtextra

0.80

 &___

0.79

ThroughAttribute

0.78

 Perſ

0.77

 XNUMX

0.77

ſelves

0.77

 Jefus

0.75

 Anſ

0.74

Activations Density 0.498%

important organizations, institutions, or entities within a context

Preceding a location, company, or brand name

company and brand names

No Comments

No Known Activations