INDEX

Explanations

numerical data or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 referenties

-0.85

Personendaten

-0.84

 cdti

-0.83

<bos>

-0.82

Vidite

-0.80

="@+

-0.77

 tdci

-0.76

ertale

-0.73

 tfsi

-0.72

protoimpl

-0.72

POSITIVE LOGITS

0.70

 yesterday

0.56

my

0.56

yesterday

0.55

few

0.51

feels

0.50

0.49

0.48

 Feels

0.48

 вчера

0.47

Activations Density 0.436%

numerical data or statistics

No Comments

No Known Activations