INDEX

Explanations

programming and API-related vocabulary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

msgTypes

-0.52

кож

-0.52

хьтан

-0.50

Def

-0.48

 iArr

-0.47

']));

-0.46

 فريبيس

-0.46

</h5>

-0.43

 poil

-0.42

</em>

-0.42

POSITIVE LOGITS

جغرافيا

0.76

SBATCH

0.73

istoitu

0.71

 ſtate

0.66

 fevere

0.65

Населення

0.62

seamnă

0.61

 poffe

0.61

IsContent

0.61

IsMutable

0.60

Activations Density 0.302%

programming and API-related vocabulary

No Comments

No Known Activations