INDEX

Explanations

technical terms and programming-related keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

<eos>

-1.07

...

-0.77

 ....

-0.75

 [...]

-0.68

[...]

-0.68

 .....

-0.67

:...

-0.66

....

-0.65

...."

-0.64

mıştır

-0.62

POSITIVE LOGITS

 AssemblyCulture

0.90

^(@)

0.87

+#+

0.80

bibfield

0.78

 disambiguazione

0.78

 Roskov

0.76

 createState

0.76

EndInit

0.74

 doubtnut

0.73

ſelf

0.73

Activations Density 5.880%

technical terms and programming-related keywords

No Comments

No Known Activations