INDEX

Explanations

terms related to criteria and standards 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Carry

-0.54

hirt

-0.50

 Akte

-0.48

 Carry

-0.48

ssize

-0.48

 Forward

-0.47

╰

-0.47

 tanul

-0.47

Confirmed

-0.47

Forward

-0.46

POSITIVE LOGITS

 criteria

1.52

 requirements

1.51

 standards

1.49

requirements

1.27

 criterion

1.25

 Criteria

1.21

standards

1.21

 thresholds

1.20

 criter

1.20

 requirement

1.19

Activations Density 0.212%

terms related to criteria and standards in various contexts

No Comments

No Known Activations