INDEX

Explanations

occurrences of temporal indicators or introductory phrases related to time events

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

bootstrapcdn

-0.56

OGND

-0.54



-0.54

MENAFN

-0.54

 jPanel

-0.51

NOPQRST

-0.49

lahoma

-0.49

 joaat

-0.49

ніципа

-0.48

ValueGeneration

-0.47

POSITIVE LOGITS

 alternativo

0.38

Since

0.38

 pozdě

0.36

 Nación

0.36

 vuonna

0.35

Matching

0.35

After

0.34

 Tahun

0.34

Later

0.34

 roku

0.34

Activations Density 0.051%

occurrences of temporal indicators or introductory phrases related to time events

No Comments

No Known Activations