INDEX

Explanations

repeated patterns or similar structures in data

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

Followed by "return"

np_acts-logits-general · gemini-2.0-flash

code returning values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

writeFieldEnd

-0.74

enderror

-0.66

AddTagHelper

-0.61

قایناق‌لار

-0.59

]");

-0.59

 indisponible

-0.57

rapeau

-0.57

Conclusión

-0.56

()");

-0.55

PerformLayout

-0.54

POSITIVE LOGITS

 noires

0.52

 ***!

0.52

Бахар

0.48

!*\

0.47

Quo

0.47

 Kram

0.47

 NDEBUG

0.47

 secco

0.46

 Borderlands

0.46

 daqui

0.45

Activations Density 0.018%

repeated patterns or similar structures in data

Followed by "return"

code returning values

No Comments

No Known Activations