INDEX

Explanations

words related to specific historical and cultural entities, especially those pertaining to German-speaking regions and Lutheranism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 myſelf

-0.61

 Behav

-0.56

 Jefus

-0.55

LabelTagHelper

-0.54

 جغرافيا

-0.52

évaluateur

-0.51

 Retail

-0.50

 везе

-0.50

 ſeveral

-0.49

 reaſon

-0.49

POSITIVE LOGITS

findpost

0.74

 Roskov

0.73

 otomatig

0.71

 Burnett

0.66

 nakalista

0.66

Petra

0.62

Karl

0.60

Siemens

0.59

 Lightboxes

0.59

PasswordEncoder

0.58

Activations Density 2.652%

words related to specific historical and cultural entities, especially those pertaining to German-speaking regions and Lutheranism

No Comments

No Known Activations