INDEX

Explanations

references to interviews and discussions about people's careers and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 autorytatywna

-0.84

Autoritní

-0.71

rrggbb

-0.63

Biblia

-0.62

 nonUne

-0.60

lusconi

-0.59

MigrationBuilder

-0.58

 coûte

-0.57

 مرئيه

-0.57

 समीक्षाओं

-0.57

POSITIVE LOGITS

 interview

2.01

 Interview

1.81

Interview

1.78

 interviewed

1.76

interview

1.72

 interviews

1.68

 interviewer

1.62

 INTERVIEW

1.61

 entrevista

1.49

Entrevista

1.44

Activations Density 0.134%

references to interviews and discussions about people's careers and experiences

No Comments

No Known Activations