INDEX

Explanations

items related to difficulty in social interaction or communication

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows "in" or "a"

np_acts-logits-general · gemini-2.0-flash

in capitalized words

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 שוליים

-0.50

脚注の使い方

-0.48

 NSCoder

-0.48

ніципалі

-0.47

 HasFactory

-0.44

awtextra

-0.44

出版年

-0.41

PDOException

-0.40

licazione

-0.40

पया

-0.40

POSITIVE LOGITS

ELTS

0.52

MessageOf

0.51

 bershka

0.49

 fibre

0.46

 culte

0.44

Prag

0.44

 CreateTagHelper

0.44

BAU

0.43

 refriger

0.43

Cmp

0.43

Activations Density 0.057%

items related to difficulty in social interaction or communication

Follows "in" or "a"

in capitalized words

No Comments

No Known Activations