INDEX

Explanations

phrases and references related to assumptions in academic or scientific contexts

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

stating assumptions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

Brainz

-0.60

 Protobuf

-0.47

GraphicsUnit

-0.46

Legături

-0.45

forgettable

-0.45

readable

-0.40

ⓧ

-0.39

 readable

-0.39

Zunanje

-0.39

 Италијани

-0.38

POSITIVE LOGITS

 assumptions

1.16

 Assumptions

1.13

Assumptions

1.02

 assumption

0.93

 Assumption

0.90

Assumption

0.90

assumption

0.75

umptions

0.72

 hypothesis

0.68

 assumed

0.66

Activations Density 0.082%

phrases and references related to assumptions in academic or scientific contexts

stating assumptions

No Comments

No Known Activations