INDEX

Explanations

terms related to relationships and correlations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Against

-1.08

Against

-1.02

Between

-0.92

 Between

-0.91

 Around

-0.88

 Behind

-0.88

 Across

-0.88

Across

-0.88

omitempty

-0.83

 Ahead

-0.82

POSITIVE LOGITS

bew

0.73

 bete

0.73

be

0.70

 bety

0.68

bet

0.66

 betre

0.65

bet

0.60

ber

0.58

0.56

Bet

0.54

Activations Density 0.429%

terms related to relationships and correlations

No Comments

No Known Activations