INDEX

Explanations

phrases related to actions and measures being proposed or taken in response to issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 հղումներ

-0.56

queens

-0.51

 useHistory

-0.49

survi

-0.48

bh

-0.47

expandindo

-0.47

AutoField

-0.46

 factura

-0.46

 يتيمه

-0.45

 fiss

-0.45

POSITIVE LOGITS

 actions

1.01

 Maßnahmen

0.94

 measures

0.94

 action

0.92

 Actions

0.91

actions

0.90

maßnahmen

0.89

措施

0.88

Measures

0.87

 ACTION

0.86

Activations Density 0.374%

phrases related to actions and measures being proposed or taken in response to issues

No Comments

No Known Activations