INDEX

Explanations

terms related to academic and professional training programs

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

professional training stages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 Skyl

-0.56

variates

-0.53

Cyfeiriadau

-0.53

 CreateTagHelper

-0.51

covo

-0.50

tyl

-0.50

regu

-0.50

ophila

-0.48

 Biblia

-0.48

mys

-0.48

POSITIVE LOGITS

 فريبيس

0.75

 internship

0.72

 vacanza

0.70

 متعلقه

0.67

 internships

0.65

 externs

0.63

 ErrIntOverflow

0.62

SBATCH

0.60

ftagPool

0.60

 prawda

0.59

Activations Density 0.042%

terms related to academic and professional training programs

professional training stages

No Comments

No Known Activations