INDEX

Explanations

phrases that imply roles or functions within 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 @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 nahilalakip

-0.80

UnknownFieldSet

-0.69

 تانيه

-0.69

 continuant

-0.64

IndentedString

-0.63

ficulties

-0.61

 يتيمه

-0.59

 kohdetta

-0.59

Anyhow

-0.59

 "/")

-0.58

POSITIVE LOGITS

CodeAnalysis

0.60

AnchorStyles

0.57

 UITableView

0.53

ρισσότε

0.52

graphicx

0.52

coltura

0.51

`{.

0.50

énier

0.49

ển

0.48

 useStyles

0.48

Activations Density 0.283%

phrases that imply roles or functions within various contexts

No Comments

No Known Activations