INDEX

Explanations

terms related to biological processes, particularly involving cellular responses and immune functions

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

 seamlessly

-0.53

 anyways

-0.51

?!

-0.50

Anyways

-0.49

redacted

-0.48

loroethane

-0.48

 Anyways

-0.47

-0.46

POSITIVE LOGITS

 &___

0.97

TintMode

0.96

OGND

0.94

MigrationBuilder

0.89

EDEFAULT

0.82

 LoggerFactory

0.81

postsleuth

0.80

 ་་

0.80

 GenerationType

0.75

 ویکی‌پدی

0.75

Activations Density 0.435%

terms related to biological processes, particularly involving cellular responses and immune functions

No Comments

No Known Activations