INDEX

Explanations

instances of self-referential expressions or phrases indicating personal experience

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

Contributed

-0.49

 Corso

-0.49

 băr

-0.47

iliano

-0.46

ئية

-0.45

 bukti

-0.44

ئي

-0.44

 oamenii

-0.43

nuit

-0.42

 unsolved

-0.42

POSITIVE LOGITS

Diweddarwch

0.88

AccessorTable

0.76

oredCriteria

0.68

InitVars

0.66

 للمعارف

0.65

UserScript

0.65

adaptiveStyles

0.63

messageInfo

0.62

principalTable

0.61

Билгалдахарш

0.61

Activations Density 0.188%

instances of self-referential expressions or phrases indicating personal experience

No Comments

No Known Activations