INDEX

Explanations

numerical values and indicators of evaluation or comparison

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

Comes before a new sentence/statement

np_acts-logits-general · gemini-2.0-flash

sentence punctuation followed by transition

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

 الرياضيه

-0.66

 Dabei

-0.65

 zunächst

-0.57

Dabei

-0.55

 Specifically

-0.53

specifically

-0.50

中略

-0.50

ám

-0.50

 lämp

-0.49

ggak

-0.49

POSITIVE LOGITS

 Anyways

1.30

 Anyway

1.27

Anyway

1.23

Anyways

1.15

 anyways

1.12

 anyway

1.07

 تانيه

0.94

 Again

0.93

Again

0.92

anyway

0.92

Activations Density 0.284%

numerical values and indicators of evaluation or comparison

Comes before a new sentence/statement

sentence punctuation followed by transition

No Comments

No Known Activations