INDEX

Explanations

sections of code or programming language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

portál

-0.61

reportWebVitals

-0.61

begre

-0.59

dillos

-0.58

 >=",

-0.56

trust

-0.55

Utf

-0.55

 Fick

-0.55

 Budi

-0.54

 néz

-0.54

POSITIVE LOGITS

endphp

1.03

1.00

0.96

0.93

0.91

0.89

0.87

0.80

0.75

UrlResolution

0.71

Activations Density 0.536%

sections of code or programming language syntax

No Comments

No Known Activations