INDEX

Explanations

legal and formal language related to liability and disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

-0.58

-0.53

 Fortunately

-0.52

Fortunately

-0.52

Luckily

-0.52

He

-0.52

 Luckily

-0.51

tidae

-0.50

de

-0.49

POSITIVE LOGITS

 purpoſe

0.97

 pleaſure

0.94

 Shakspeare

0.92

 auroit

0.82

 cauſe

0.80

 Majefty

0.80

 feroit

0.79

 ſtate

0.78

 Diſ

0.77

 Jefus

0.77

Activations Density 0.032%

legal and formal language related to liability and disclaimers

No Comments

No Known Activations