INDEX

Explanations

phrases and expressions that indicate a lack of concern or motivation to act

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

UnusedPrivate

-0.84

URLException

-0.81

 Normdatei

-0.78

NUMX

-0.77

*/

-0.76

SequentialGroup

-0.76

``.

-0.76

 ویکی‌آمباردا

-0.75

()]

-0.74

HomeAsUpEnabled

-0.72

POSITIVE LOGITS

 anyone

0.86

anyone

0.65

 anybody

0.64

 whoever

0.63

 кто

0.63

Who

0.62

Anyone

0.60

Who

0.60

 Anyone

0.58

誰

0.58

Activations Density 0.142%

phrases and expressions that indicate a lack of concern or motivation to act

No Comments

No Known Activations