INDEX

Explanations

mentions of "all" or "any" with other words

oai_token-act-pair · gemini-2.0-flash

all

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

all

-0.84

All

-0.75

all

-0.75

 referenties

-0.66

All

-0.65

 Tất

-0.63

ALL

-0.62

 todas

-0.57

 Semua

-0.56

 ComVisible

-0.55

POSITIVE LOGITS

but

1.16

 lakini

0.77

 maar

0.77

 pero

0.76

BUT

0.74

 tetapi

0.74

But

0.71

 tapi

0.68

But

0.68

 nhưng

0.67

Activations Density 4.895%

mentions of "all" or "any" with other words

all

No Comments

No Known Activations

mentions of "all" or "any" with other words

all

No Comments

No Known Activations