INDEX

Explanations

terms related to "non-"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Beſ

-0.88

 itſelf

-0.87

 Theſe

-0.85

 Vikipedi

-0.82

myModal

-0.78

 proprement

-0.77

 ainfi

-0.77

 ſche

-0.76

DockStyle

-0.76

 imprimée

-0.75

POSITIVE LOGITS

non

2.19

Non

2.08

Non

2.07

non

1.99

NON

1.93

NON

1.70

非

1.68

 nons

1.38

非

1.34

 Nons

1.33

Activations Density 0.089%

terms related to "non-"

No Comments

No Known Activations