INDEX

Explanations

commas, conjunctions, and prepositions

oai_token-act-pair · gemini-2.0-flash

the word "instead"

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

Contrasting ideas or thoughts

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

hede

-0.51

 none

-0.47

 hadn

-0.46

niv

-0.44

 ninguna

-0.44

必要

-0.43

 None

-0.43

 Doesn

-0.42

 никого

-0.42

pektrum

-0.42

POSITIVE LOGITS

 instead

0.85

Instead

0.81

instead

0.78

 Instead

0.75

StructEnd

0.71

rungsseite

0.68

 CreateTagHelper

0.67

 zamiast

0.67

uttosto

0.66

 merely

0.66

Activations Density 4.760%

commas, conjunctions, and prepositions

the word "instead"

Contrasting ideas or thoughts

No Comments

No Known Activations