INDEX

Explanations

references to experimental results and data, particularly those concerning omitted or non-presented information

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

"data not shown"

np_acts-logits-general · gemini-2.0-flash

data not shown

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

+#+#

-0.97

PyExc

-0.85

+:+

-0.72

RenderAtEndOf

-0.71

PerformLayout

-0.69

GIVEREF

-0.69

///</

-0.68

\{\\

-0.68

 <<<<<<<<<<<<<<

-0.65

'));

-0.64

POSITIVE LOGITS

not

0.68

 unnamed

0.56

 anonymous

0.56

 anonymity

0.54

0.52

anonymous

0.50

not

0.49

NOT

0.49

 OMITTED

0.49

 nicht

0.47

Activations Density 0.436%

references to experimental results and data, particularly those concerning omitted or non-presented information

"data not shown"

data not shown

No Comments

No Known Activations