INDEX

Explanations

phrases related to interviews and professional discussions

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

Texts containing interviews

np_acts-logits-general · gemini-2.0-flash

interview or talk

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 NgModule

-0.54

 förslag

-0.52

 لينك

-0.51

NgModule

-0.51

 enfans

-0.49

 示例

-0.49

urnia

-0.48

 Suggestion

-0.48

WarningLevel

-0.48

 Kenntnis

-0.48

POSITIVE LOGITS

 interview

2.97

 interviews

2.67

 Interview

2.67

Interview

2.60

interview

2.59

 interviewed

2.56

 INTERVIEW

2.35

 Interviews

2.33

 interviewing

2.27

Interviews

2.23

Activations Density 0.278%

phrases related to interviews and professional discussions

Texts containing interviews

interview or talk

No Comments

No Known Activations