INDEX

Explanations

references to historical time periods, particularly the early to mid-20th century

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 early

-1.53

early

-1.41

 Early

-1.38

Early

-1.38

 EARLY

-1.27

EARLY

-1.21

 frühen

-0.98

早期

-0.94

 earliest

-0.90

 früh

-0.82

POSITIVE LOGITS

 tslint

0.68

béco

0.65

 AdapterView

0.65

quelize

0.64

ConstraintMaker

0.61

 psycopg

0.59

nvarchar

0.59

Referanser

0.59

aliana

0.58

 يتيمه

0.56

Activations Density 0.134%

references to historical time periods, particularly the early to mid-20th century

No Comments

No Known Activations