INDEX

Explanations

mentions of trade and trading-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-1.15

 Monfieur

-1.13

 raiſ

-1.13

 Jefus

-1.10

ſelf

-1.09

 pleaſure

-1.08

Efq

-1.06

 itſelf

-1.03

 ſever

-1.03

 becauſe

-0.99

POSITIVE LOGITS

 trade

3.13

 Trade

2.66

trade

2.61

Trade

2.58

 TRADE

2.44

TRADE

2.19

 trades

2.11

 trading

2.07

 traded

1.83

trades

1.75

Activations Density 0.098%

mentions of trade and trading-related terms

No Comments

No Known Activations