INDEX

Explanations

programming-related terminology and functions

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

"It" as a subject or object

np_acts-logits-general · gemini-2.0-flash

things not working

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 natin

-0.64

 your

-0.60

[`

-0.60

 propOrder

-0.58

 jūs

-0.58

archiviato

-0.57

 yourself

-0.56

 ourselves

-0.56

 vostra

-0.55

bilirsiniz

-0.55

POSITIVE LOGITS

 seems

0.72

 Tried

0.71

 bekomme

0.69

 correctly

0.64

 doesnt

0.64

 seem

0.63

 pourtant

0.63

 everything

0.63

tried

0.63

Tried

0.62

Activations Density 1.247%

programming-related terminology and functions

"It" as a subject or object

things not working

No Comments

No Known Activations