INDEX

Explanations

content related to market analysis and investment recommendations

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

Abbreviations for company names

np_acts-logits-general · gemini-2.0-flash

analysts and HS

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 roll

-0.43

roll

-0.42

cuadro

-0.41

えん

-0.41

rol

-0.41

 Glaser

-0.41

FEATURES

-0.41

glVertex

-0.40

 TEST

-0.40

oxy

-0.40

POSITIVE LOGITS

 analyst

1.41

 analysts

1.41

analyst

1.15

Analyst

1.14

 Analyst

1.14

 Analysts

1.11

Analysts

1.10

 research

0.86

analy

0.86

 analys

0.85

Activations Density 0.084%

content related to market analysis and investment recommendations

Abbreviations for company names

analysts and HS

No Comments

No Known Activations