INDEX

Explanations

words related to health conditions and food items

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

ending with "like" or similar suffixes

np_acts-logits-general · gemini-2.0-flash

describing things as X-like

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

InitVars

-0.63

 ModelExpression

-0.59

تفصیلات

-0.58

发表于

-0.57

requestCode

-0.55

 الدولى

-0.54

ništ

-0.54

 AssemblyCulture

-0.53

 CreateTagHelper

-0.52

TagMode

-0.52

POSITIVE LOGITS

like

1.89

LIKE

1.43

esque

1.41

Like

1.32

 style

1.27

 like

1.27

ähn

1.20

 benzer

1.20

 looking

1.20

style

1.17

Activations Density 0.670%

words related to health conditions and food items

ending with "like" or similar suffixes

describing things as X-like

No Comments

No Known Activations