INDEX

Explanations

variations of doubt, uncertainty, and conditionality in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

batore

-0.67

 jScrollPane

-0.63

 véritable

-0.63

 inoltre

-0.62

 سكانية

-0.60

getWriter

-0.60

NewUrlParser

-0.59

styleUrls

-0.59

stdc

-0.58

érience

-0.57

POSITIVE LOGITS

sizeCache

0.56

entibus

0.55

 neceffary

0.54

 fevere

0.53

enschappelijke

0.48

 Reſ

0.48

 Diſ

0.46

 marte

0.45

 ſtate

0.45

しても

0.44

Activations Density 0.275%

variations of doubt, uncertainty, and conditionality in statements

No Comments

No Known Activations