INDEX

Explanations

references to job positions and their associated roles or qualifications

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

 AppCompatTheme

-0.49

 protoimpl

-0.49

出版年

-0.47

+#+

-0.44

stickers

-0.42

 flakes

-0.42

 alleys

-0.41

RTHOOK

-0.41

keur

-0.40

canestro

-0.40

POSITIVE LOGITS

 position

0.96

 Position

0.88

 positions

0.84

 POSITION

0.81

 role

0.81

 Positions

0.81

Position

0.79

 roles

0.79

position

0.73

Positions

0.73

Activations Density 0.338%

references to job positions and their associated roles or qualifications

No Comments

No Known Activations