INDEX

Explanations

mentions of interviews and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 propOrder

-0.92

zd

-0.75

жалуйста

-0.63

 Watkins

-0.62

 ridurre

-0.62

getP

-0.61

AppendLine

-0.61

дожник

-0.61

 sorella

-0.60

жды

-0.59

POSITIVE LOGITS

 interviews

1.53

 INTERVIEW

1.53

 Interview

1.50

 interview

1.49

Interview

1.45

 interviewing

1.41

INTERVIEW

1.39

 Interviews

1.39

interview

1.31

 interviewer

1.29

Activations Density 0.059%

mentions of interviews and related contexts

No Comments

No Known Activations