INDEX

Explanations

references to personal and professional careers

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

before "career"

np_acts-logits-general · gemini-2.0-flash

his career

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

AccessorTable

-0.61

 Wikimedijinoj

-0.51

 فريبيس

-0.50

NOPQRST

-0.46

 שוליים

-0.46

 typelib

-0.46

ValueGeneration

-0.45

MessageOf

-0.43

BagConstraints

-0.43

VISION

-0.43

POSITIVE LOGITS

 career

2.16

career

1.82

 careers

1.77

 carrière

1.71

Career

1.63

 Career

1.54

 carreira

1.50

 carriera

1.45

 CAREER

1.43

 Karriere

1.42

Activations Density 0.103%

references to personal and professional careers

before "career"

his career

No Comments

No Known Activations