INDEX

Explanations

references to quantities or proportions

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

lardır

-0.67

 noastre

-0.67

 flotte

-0.66

 pleaſure

-0.65

 poffible

-0.64

 chofe

-0.64

μως

-0.63

:+:

-0.63

ucap

-0.60

 إنه

-0.59

POSITIVE LOGITS

 which

0.90

which

0.71

 MessageBoxIcon

0.63

styleType

0.63

 Which

0.61

SequentialGroup

0.61

Which

0.61

 whose

0.59

FormTagHelper

0.58

 AssemblyCulture

0.56

Activations Density 0.198%

references to quantities or proportions

No Comments

No Known Activations