INDEX

Explanations

phrases indicating the need for additional research or exploration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Koe

-0.82

setContentType

-0.77

kranz

-0.75

 McDonough

-0.69

ordnung

-0.69

 Sanz

-0.67

DOCTYPE

-0.67

 httpClient

-0.65

Lyd

-0.65

ActionEvent

-0.65

POSITIVE LOGITS

 further

1.46

further

1.45

urther

1.44

FURTHER

1.38

Further

1.37

 Further

1.35

 FURTHER

1.30

进一步

1.16

 farther

0.91

 furthering

0.91

Activations Density 0.103%

phrases indicating the need for additional research or exploration

No Comments

No Known Activations