INDEX

Explanations

elements related to grading or scores in an educational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.91

-0.70

 nine

-0.70

 Nine

-0.67

Nine

-0.60

-0.59

kusen

-0.56

 NINE

-0.56

 otomatig

-0.56

nine

-0.55

POSITIVE LOGITS

1.08

0.67

 Third

0.66

0.64

 third

0.58

 THIRD

0.56

 третий

0.56

 troisième

0.54

ंदीखरीदारी

0.54

Third

0.53

Activations Density 0.030%

elements related to grading or scores in an educational context

No Comments

No Known Activations