INDEX

Explanations

specific attributes and properties of classes and their relationships in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fycat

-0.58

-0.51

Chham

-0.48

van

-0.47

«

-0.47

escens

-0.46

?),

-0.46

 extra

-0.45

 betweenstory

-0.44

tesy

-0.44

POSITIVE LOGITS

 myſelf

0.93

 purpoſe

0.93

 themſelves

0.87

 pleaſure

0.85

 itſelf

0.83

 preſent

0.81

 ſtate

0.81

 Monfieur

0.80

 greateſt

0.80

 ſeveral

0.79

Activations Density 0.027%

specific attributes and properties of classes and their relationships in code

No Comments

No Known Activations