INDEX

Explanations

references to training, education, and skill development in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Sonora

-0.45

 Dermatologist

-0.45

brk

-0.45

ommt

-0.44

헌

-0.44

GHI

-0.44

estanden

-0.44

 vant

-0.43

 века

-0.43

griffen

-0.43

POSITIVE LOGITS

 training

1.21

training

1.06

 Training

1.05

Training

1.00

 trainings

0.98

 TRAINING

0.92

 Trainings

0.92

TRAINING

0.90

 pelatihan

0.83

 capacitación

0.77

Activations Density 0.156%

references to training, education, and skill development in various contexts

No Comments

No Known Activations