INDEX

Explanations

emphatic affirmations and references to sharpness in descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Kwan

-0.79

Rhestr

-0.78

Fans

-0.77

 Gallen

-0.77

 Fenton

-0.76

 riuscito

-0.75

 Lipa

-0.73

Venus

-0.73

pausal

-0.73

hnia

-0.73

POSITIVE LOGITS

 Garg

0.80

Tos

0.75

Leopold

0.75

 Leopold

0.74

 UIFont

0.73

omitempty

0.71

onha

0.68

Erfolge

0.66

 Bertie

0.66

 Fleck

0.65

Activations Density 0.363%

emphatic affirmations and references to sharpness in descriptions

No Comments

No Known Activations