INDEX

Explanations

references to time and historical context

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

decades

np_acts-logits-general · gemini-2.0-flash

past decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 transfieras

-0.75

 estimés

-0.66

parsedMessage

-0.61

styleUrls

-0.60

MemoryWarning

-0.60

mybatisplus

-0.59

MLLoader

-0.59

 препратки

-0.59

InSection

-0.58

 ويكيميديا

-0.58

POSITIVE LOGITS

decade

1.29

 decades

1.08

decade

1.04

Dec

0.98

Dec

0.98

 half

0.98

DEC

0.97

dec

0.95

Decade

0.88

DEC

0.84

Activations Density 0.156%

references to time and historical context

decades

past decades

No Comments

No Known Activations

references to time and historical context

decades

past decades

No Comments

No Known Activations