INDEX

Explanations

terms and concepts related to methods, frameworks, and procedural elements in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Sa

-0.47

Re

-0.46

ος

-0.45

lový

-0.44

ava

-0.43

’

-0.43

Encyclopædia

-0.43

sa

-0.42

jst

-0.41

demi

-0.41

POSITIVE LOGITS

 nakalista

0.86

 ſche

0.83

 neceff

0.80

úsqueda

0.80

 deſt

0.79

 ✭✭

0.78

 pleaſure

0.78

ReusableCell

0.77

htbp

0.74

ViewInit

0.73

Activations Density 1.240%

terms and concepts related to methods, frameworks, and procedural elements in various contexts

No Comments

No Known Activations