INDEX

Explanations

numeric values and size specifications in relation to images or data

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

image resolution and size

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.58

NewUrlParser

-0.58

WritableDatabase

-0.55

Hentet

-0.52

RTLR

-0.46

✨:

-0.45

 ocurrido

-0.43

noopener

-0.42

SourceChecksum

-0.42

 starring

-0.41

POSITIVE LOGITS

 resolution

0.59

 image

0.49

 Resolution

0.47

resolution

0.45

 resolutions

0.45

 ingress

0.45

 RESOLUTION

0.43

]")]

0.42

Resolution

0.42

 resolu

0.42

Activations Density 0.014%

numeric values and size specifications in relation to images or data

image resolution and size

No Comments

No Known Activations