INDEX

Explanations

terms related to charging and energy usage

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

theless

-1.01

 doubtnut

-0.89

\"");

-0.89

>\<

-0.88

 Romain

-0.87

 myſelf

-0.85

 bint

-0.85

 OBITUARY

-0.85

✨:

-0.85

 cdti

-0.84

POSITIVE LOGITS

 charges

2.08

 charge

2.07

charge

1.95

 Charge

1.90

Charge

1.87

 Charges

1.85

charges

1.84

 charged

1.79

 CHARGE

1.75

Charges

1.73

Activations Density 0.040%

terms related to charging and energy usage

No Comments

No Known Activations