INDEX

Explanations

phrases indicating consistency or stability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

صالات

-0.49

OfBirth

-0.48

 gezegd

-0.46

karna

-0.46

 ум

-0.45

IRUS

-0.44

pom

-0.43

 plain

-0.43

Observation

-0.43

usehen

-0.43

POSITIVE LOGITS

 stable

1.64

 stability

1.54

stable

1.47

stability

1.45

 Stability

1.43

 stabilité

1.42

 Stable

1.40

Stable

1.35

Stability

1.31

 stabilize

1.30

Activations Density 0.078%

phrases indicating consistency or stability

No Comments

No Known Activations

phrases indicating consistency or stability

No Comments

No Known Activations