INDEX

Explanations

occurrences of the word "you" along with nearby pronouns or words similar to "as"

oai_token-act-pair · gemini-2.0-flash

programming-related keywords or phrases

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

зулта

-0.49

 متعلقه

-0.47

 rusty

-0.46

 extrinsic

-0.44

iphery

-0.44

ритори

-0.41

 facility

-0.41

 Pilate

-0.40

 Cowper

-0.40

 SEDS

-0.40

POSITIVE LOGITS

windowFixed

0.80

ISupport

0.64

ExtendWith

0.63

tvguidetime

0.63

 estimés

0.57

+#+

0.56

CardContent

0.56

AutoField

0.55

 okuyayım

0.55

はじめに

0.54

Activations Density 0.964%

occurrences of the word "you" along with nearby pronouns or words similar to "as"

programming-related keywords or phrases

No Comments

No Known Activations