INDEX

Explanations

terms related to mold and casting processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 defaultstate

-0.76

 betweenstory

-0.68

AndEndTag

-0.63

ьаж

-0.60

 nonUne

-0.59

 Савезне

-0.54

setVerticalGroup

-0.54

 dAtA

-0.52

expandindo

-0.52

 linkovi

-0.50

POSITIVE LOGITS

 mold

0.85

 molds

0.79

 moulds

0.74

 mould

0.74

Mold

0.71

 moldes

0.70

mold

0.67

 moule

0.67

 Mould

0.65

 Mold

0.59

Activations Density 0.356%

terms related to mold and casting processes

No Comments

No Known Activations