INDEX

Explanations

phrases indicating recent actions or events

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

 eventually

-0.51

ource

-0.46

 liegen

-0.44

eventually

-0.43

 eventual

-0.42

้อย

-0.42

 weitere

-0.42

 ultimately

-0.41

 vägen

-0.41

kün

-0.41

POSITIVE LOGITS

RegistryLite

0.98

 kasarigan

0.82

 resourceCulture

0.82

 Newly

0.80

Newly

0.80

IVEREF

0.79

featureID

0.79

principalColumn

0.79

IndentedString

0.77

 newly

0.75

Activations Density 0.122%

phrases indicating recent actions or events

No Comments

No Known Activations