INDEX

Explanations

expressions of user satisfaction and product usability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

findpost

-0.50

 EconPapers

-0.48

ⓧ

-0.46

 cherchés

-0.45

RectangleBorder

-0.45

 дописавши

-0.45

RuleContext

-0.44

DebuggerNonUser

-0.43

 مشين

-0.42

Personensuche

-0.42

POSITIVE LOGITS

Bought

0.37

aarrggbb

0.36

thick

0.36

 thicker

0.35

purchased

0.34

 createSlice

0.34

 thick

0.33

 Purchased

0.33

bundled

0.33

PhysRev

0.32

Activations Density 0.121%

expressions of user satisfaction and product usability

No Comments

No Known Activations