INDEX

Explanations

references to individuals and their achievements or statements in documents

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

 müßte

-0.76

 muß

-0.71

(;;)

-0.62

 mußte

-0.61

Retired

-0.61

 läßt

-0.60

 retired

-0.60

退休

-0.58

Retirement

-0.57

uxxxx

-0.56

POSITIVE LOGITS

Personensuche

0.69

 barista

0.68

 internship

0.66

 graduate

0.65

 internships

0.65

 interns

0.64

 étudiant

0.63

 Graduate

0.61

 étudi

0.60

 externs

0.60

Activations Density 0.397%

references to individuals and their achievements or statements in documents

No Comments

No Known Activations