INDEX

Explanations

terms related to wealth and social class distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Personendaten

-0.84

DeleteMapping

-0.77

 betweenstory

-0.69

RenderAtEndOf

-0.67

 <=",

-0.66

ConstraintMaker

-0.66

 ujednoznacz

-0.65

PyExc

-0.65

 Cervantes

-0.63

 Finlande

-0.62

POSITIVE LOGITS

 rich

1.00

 Rich

0.99

 RICH

0.97

rich

0.94

Rich

0.93

 POOR

0.89

 Poor

0.86

RICH

0.83

Poor

0.80

 poor

0.79

Activations Density 0.105%

terms related to wealth and social class distinctions

No Comments

No Known Activations