INDEX

Explanations

terms related to permissions, limits, and expected values in various contexts

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

 than

-0.35

 while

-0.35

 Either

-0.34

 pernas

-0.34

flexDirection

-0.34

 tableName

-0.33

 either

-0.33

 ventajas

-0.33

por

-0.31

 that

-0.31

POSITIVE LOGITS

styleable

0.71

المناصب

0.68

DockStyle

0.65

twimg

0.63

WebElementEntity

0.62

ſelves

0.62

LLocation

0.62

 nakalista

0.61

BagConstraints

0.61

setPreferred

0.60

Activations Density 0.825%

terms related to permissions, limits, and expected values in various contexts

No Comments

No Known Activations