INDEX

Explanations

information related to trading strategies and techniques

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

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

RegressionTest

-0.61

transQ

-0.55

+#+#

-0.52

+:+

-0.51

 Económica

-0.50

principalColumn

-0.50

PrototypeOf

-0.48

 चीज़ों

-0.47

 genealog

-0.47

AGB

-0.46

POSITIVE LOGITS

 holdings

1.08

 holding

0.86

 buys

0.86

 positions

0.83

 exposure

0.81

 portfolio

0.80

 buying

0.80

holdings

0.80

 position

0.79

 bought

0.79

Activations Density 0.125%

information related to trading strategies and techniques

No Comments

No Known Activations