INDEX

Explanations

personal experiences and self-reflection

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

Follows "I" or contains the word "that"

np_acts-logits-general · gemini-2.0-flash

i had never

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 defaultstate

-0.85

parsedMessage

-0.70

windowFixed

-0.68

WithIOException

-0.67

Aiheesta

-0.64

EndGlobalSection

-0.64

SharedDtor

-0.60

 متعلقه

-0.56

colgroup

-0.56

 ivelany

-0.56

POSITIVE LOGITS

 hadn

1.07

 unsus

0.96

 never

0.88

 desconoc

0.86

 Didn

0.86

没想到

0.84

 didn

0.84

 previously

0.80

Unexpected

0.80

 unexpected

0.80

Activations Density 0.231%

personal experiences and self-reflection

Follows "I" or contains the word "that"

i had never

No Comments

No Known Activations