INDEX

Explanations

instances of positive emotional experiences or descriptions

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

Summarizing statements or brief explanations ending in "was" or "is"

np_acts-logits-general · gemini-2.0-flash

summarizing or concluding statements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 numerus

-0.59

 كومونز

-0.57

 poveznice

-0.56

 correctes

-0.56

 perſon

-0.56

enumi

-0.55

 Hoon

-0.55

WebElementEntity

-0.55

NewUrlParser

-0.54

POSITIVE LOGITS

Bref

0.81

 Altogether

0.69

ExecuteReader

0.67

ruptedException

0.66

SharedDtor

0.65

まさに

0.63

overall

0.62

這就是

0.61

难怪

0.61

Voilà

0.58

Activations Density 0.220%

instances of positive emotional experiences or descriptions

Summarizing statements or brief explanations ending in "was" or "is"

summarizing or concluding statements

No Comments

No Known Activations