INDEX

Explanations

historical references and interpretations within texts

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

Following "accounts," "historian," or "by"

np_acts-logits-general · gemini-2.0-flash

according to historical sources

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

Autoritní

-0.64

ScopeManager

-0.62

parsedMessage

-0.60

 resourceCulture

-0.59

Identyfik

-0.57

AxisAlignment

-0.57



-0.56

VersionUID

-0.56

انتهای

-0.54

submenu

-0.54

POSITIVE LOGITS

 accounts

0.84

 records

0.81

 tradition

0.80

 extant

0.78

accounts

0.76

tradition

0.74

 sources

0.74

 historians

0.73

Accounts

0.72

 mentions

0.72

Activations Density 0.364%

historical references and interpretations within texts

Following "accounts," "historian," or "by"

according to historical sources

No Comments

No Known Activations