INDEX

Explanations

references to specific products and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 ſind

-0.89

^(@)

-0.79

WebServlet

-0.77

]),

-0.75

Portale

-0.74

.",

-0.72

resaid

-0.71

 iſt

-0.69

 totalPrice

-0.69

'}>

-0.69

POSITIVE LOGITS

.....

0.75

....

0.75

0.66

0.65

!!!!

0.65

0.63

!!

0.63

......

0.61

 thing

0.61

Activations Density 0.653%

references to specific products and their characteristics

No Comments

No Known Activations