INDEX

Explanations

specific names or terms related to people and places

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

containing non-English characters

np_acts-logits-general · gemini-2.0-flash

Turkish names and words

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

ın

-0.60

CopyWith

-0.46

ını

-0.45

ı

-0.44

WebVitals

-0.43

 initComponents

-0.43

ımız

-0.42

:+:

-0.42

 Familienname

-0.42

liği

-0.42

POSITIVE LOGITS

 raiſ

0.73

 becauſe

0.72

luk

0.72

 AssemblyCulture

0.67

 poffible

0.66

 uſe

0.66

 itſelf

0.66

@[+][

0.66

 fubject

0.66

 ſeveral

0.65

Activations Density 0.071%

specific names or terms related to people and places

containing non-English characters

Turkish names and words

No Comments

No Known Activations