INDEX

Explanations

financial terms related to fees and charges

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

fees or charges

np_acts-logits-general · gemini-2.0-flash

fees and charges

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

 AssemblyCompany

-0.69

 autorytatywna

-0.65

ⓧ

-0.57

prüche

-0.56

FieldBuilder

-0.53

 uLocal

-0.52

!*\

-0.51

 ObjectParameter

-0.51

SequentialGroup

-0.50

ímetros

-0.50

POSITIVE LOGITS

 fees

2.02

fee

2.01

Fee

1.73

 Fees

1.73

Fee

1.64

 charges

1.62

Fees

1.60

 charge

1.59

fee

1.58

fees

1.51

Activations Density 0.183%

financial terms related to fees and charges

fees or charges

fees and charges

No Comments

No Known Activations