INDEX

Explanations

specific mathematical symbols and Greek letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 houſe

-1.01

 purpoſe

-0.93

 pleaſure

-0.92

 whoſe

-0.92

 Monfieur

-0.90

 quæ

-0.89

 themſelves

-0.88

 Jefus

-0.88

 enfans

-0.87

 greateſt

-0.87

POSITIVE LOGITS

ω

0.61

α

0.60

msgTypes

0.57

β

0.54

σ

0.54

δ

0.53

η

0.53

)))),

0.52

γ

0.51

ε

0.50

Activations Density 0.002%

specific mathematical symbols and Greek letters

No Comments

No Known Activations