INDEX

Explanations

the word "a" following prepositions or pronouns

oai_token-act-pair · gemini-2.0-flash

unusual word patterns or terms

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

Positive emotions/actions

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

Negative Logits

Cyfeiriadau

-0.66

ModelSerializer

-0.63

Jereo

-0.63

 poveznice

-0.60

gatsby

-0.57

Autoritní

-0.57

IndentedString

-0.56

inawa

-0.54

 ejus

-0.53

 באתר

-0.52

POSITIVE LOGITS

 hint

0.53

 صوتيه

0.51

 tslint

0.48

ANTLR

0.47

soka

0.46

CloseOperation

0.46

ň

0.46

 pained

0.44

 smirk

0.43

WireFormatLite

0.43

Activations Density 1.031%

the word "a" following prepositions or pronouns

unusual word patterns or terms

Positive emotions/actions

No Known Activations