INDEX

Explanations

terms related to medicinal or electrical concepts and their mathematical multiplicities

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

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

-1.01

logical

-0.79

-0.78

ored

-0.75

к

-0.70

сь

-0.69

{\

-0.69

sive

-0.67

ized

-0.67

POSITIVE LOGITS

 ProtoMessage

1.05

0.96

AddHtmlAttribute

0.94

 transférez

0.93

 HasFactory

0.91

ьаж

0.87

IUrlHelper

0.86

 חיצוניים

0.86

Παραπομπές

0.84

 vaisselle

0.84

Activations Density 0.850%

terms related to medicinal or electrical concepts and their mathematical multiplicities

No Comments

No Known Activations