INDEX

Explanations

the prefix "en-" in words

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

starting with "En" or "en"

np_acts-logits-general · gemini-2.0-flash

words starting with En

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

 AssemblyCulture

-1.04

 nakalista

-0.89

IVEREF

-0.88

 <=",

-0.87

 Theſe

-0.82

GEBURTSDATUM

-0.82

 HasFactory

-0.81

 BrowserModule

-0.79

]")]

-0.78

DockStyle

-0.78

POSITIVE LOGITS

En

0.75

en

0.68

EN

0.65

En

0.63

enc

0.54

EN

0.51

 Enrico

0.48

 encom

0.46

en

0.46

 enro

0.46

Activations Density 0.067%

the prefix "en-" in words

starting with "En" or "en"

words starting with En

No Comments

No Known Activations