INDEX

Explanations

sequences of whitespace characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.87

teryx

-0.65

Билгалдахарш

-0.61

 nakalista

-0.61

 onOptions

-0.59

ooled

-0.58

друг

-0.58

–)

-0.55

glBegin

-0.55

POSITIVE LOGITS

 Opis

0.56

Smarty

0.53

 Newtonian

0.50

ruc

0.49

Huk

0.49

 Kanz

0.49

 Facult

0.48

 oogen

0.48

 aapt

0.48

 Boun

0.47

Activations Density 0.170%

sequences of whitespace characters

No Comments

No Known Activations