INDEX

Explanations

references to various forms of assessments or analyses related to films and data

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

preceding relative pronouns

np_acts-logits-general · gemini-2.0-flash

relative clauses

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

 kasarigan

-0.71

IVEREF

-0.70

dafx

-0.66

ِّف

-0.64

pexpr

-0.63

+#+#

-0.63

ratulations

-0.63

fycat

-0.62

 SEDS

-0.62

出版年

-0.61

POSITIVE LOGITS

 which

3.24

which

2.80

 WHICH

2.28

 Which

2.16

Which

2.15

who

1.73

ซึ่ง

1.63

 whom

1.62

hich

1.62

 whose

1.58

Activations Density 1.938%

references to various forms of assessments or analyses related to films and data

preceding relative pronouns

relative clauses

No Comments

No Known Activations

references to various forms of assessments or analyses related to films and data

preceding relative pronouns

relative clauses

No Comments

No Known Activations