INDEX

Explanations

references to wealth and economic status

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ptăm

-0.47

Numerade

-0.47

 CreateTagHelper

-0.45

entar

-0.44

 RIAA

-0.43

verständlich

-0.43

 drauf

-0.42

Ums

-0.41

 Alia

-0.41

jooq

-0.40

POSITIVE LOGITS

 Rich

2.20

 rich

2.14

Rich

2.11

 richer

1.74

rich

1.73

 RICH

1.73

RICH

1.66

 richness

1.57

 richest

1.55

 enrich

1.50

Activations Density 0.201%

references to wealth and economic status

No Comments

No Known Activations