INDEX

Explanations

instances of speaking or telling, along with some prepositions and some verbs

oai_token-act-pair · gemini-2.0-flash

prepositions and connecting words

np_token-act-pair-logits · gpt-4o-mini

say "to" or "with"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.92

Diweddarwch

-0.91

tagHelperRunner

-0.82

ScopeManager

-0.80

脚注の使い方

-0.78

RegistryLite

-0.69

 AssemblyCulture

-0.68

 Walkover

-0.68

webElementXpaths

-0.68

.*")]

-0.65

POSITIVE LOGITS

to

1.20

 unto

1.13

 kepada

1.04

 vnto

0.99

กับ

0.92

tothe

0.90

 Unto

0.77

แก่

0.73

kepada

0.70

 terhadap

0.69

Activations Density 0.897%

instances of speaking or telling, along with some prepositions and some verbs

prepositions and connecting words

say "to" or "with"

No Comments

No Known Activations