INDEX

Explanations

descriptive narratives and fictional stories

oai_token-act-pair · gemini-2.0-flash

occurrences of the word "when"

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 typelib

-0.78

AnchorStyles

-0.75

BeginContext

-0.74

uxxxx

-0.74

makeConstraints

-0.70

tagHelperRunner

-0.69

tvguidetime

-0.67

+#+

-0.65

DockStyle

-0.65

POSITIVE LOGITS

 when

0.55

when

0.48

ibol

0.47

ounded

0.47

Кол

0.47

diğinde

0.46

PhysRev

0.46

dated

0.45

姆斯

0.45

 When

0.45

Activations Density 2.476%

descriptive narratives and fictional stories

occurrences of the word "when"

No Comments

No Known Activations