INDEX

Explanations

formal logical constructs and proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<eos>

-0.55

-0.52

®

-0.47

di

-0.46

me

-0.46

“

-0.45

 past

-0.45

box

-0.45

-0.44

RequestMapping

-0.43

POSITIVE LOGITS

 RSSSF

0.90

 iprot

0.87

featureID

0.87

 mergeFrom

0.87

 propOrder

0.86

 ligiloj

0.83

setVerticalGroup

0.80

 ainfi

0.79

Chham

0.78

 Савезне

0.78

Activations Density 0.824%

formal logical constructs and proofs

No Comments

No Known Activations