INDEX

Explanations

indicators of timed events or processes

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

Text appearing before section headers or introductions

np_acts-logits-general · gemini-2.0-flash

troubleshooting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 CreateTagHelper

-0.71

parsedMessage

-0.68

Geplaatst

-0.68



-0.68

 propOrder

-0.65

ValueStyle

-0.58

 Majefty

-0.56

!")

-0.56

 jScrollPane

-0.56

attendre

-0.55

POSITIVE LOGITS

 when

0.66

 amikor

0.64

when

0.63

的时候

0.59

 cuando

0.57

geren

0.56

 berikutnya

0.56

лактика

0.56

 quando

0.56

uct

0.55

Activations Density 0.401%

indicators of timed events or processes

Text appearing before section headers or introductions

troubleshooting

No Comments

No Known Activations