INDEX

Explanations

mentions of image transformations and manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

when

-0.46

When

-0.45

 counterparts

-0.43

δί

-0.42

 when

-0.41

ften

-0.40

 cases

-0.39

ery

-0.38

 solchen

-0.38

aville

-0.38

POSITIVE LOGITS

 hObject

0.86

'{@

0.86

帖最后由

0.80

PhysRev

0.80

 AssemblyCulture

0.78

 ComVisible

0.78

RTLI

0.77

MemoryWarning

0.76

aarrggbb

0.75

withIdentifier

0.73

Activations Density 0.781%

mentions of image transformations and manipulations

No Comments

No Known Activations