INDEX

Explanations

instances of decision-making and evaluation in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Infórmanos

-0.93

RTLD

-0.80

 Reſ

-0.76

 ―――――

-0.73

 poffible

-0.71

 EClass

-0.70

ſelf

-0.69

 ſtate

-0.69

 Diſ

-0.67

ſelves

-0.67

POSITIVE LOGITS

IntoConstraints

0.57

 pretty

0.50

 only

0.47

 acordo

0.47

weist

0.46

it

0.46

ying

0.45

<bos>

0.45

 immediately

0.45

 keinem

0.44

Activations Density 0.322%

instances of decision-making and evaluation in texts

No Comments

No Known Activations