INDEX

Explanations

words related to uncertainty or speculation

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

likely, perceived, or qualified statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

ambién

-0.46

 nonUne

-0.44

 '\\;'

-0.43

 dokun

-0.41

BeginContext

-0.41

principalTable

-0.40

gameserver

-0.39

 tajam

-0.39

 vaisselle

-0.39

 réglementation

-0.37

POSITIVE LOGITS

Personensuche

0.51

 insuffisamment

0.46

stdc

0.44

 Shaq

0.41

setLayoutParams

0.41

twimg

0.41

 Chwiliwch

0.40

 Photocase

0.40

openConnection

0.39

iotensin

0.39

Activations Density 0.155%

words related to uncertainty or speculation

likely, perceived, or qualified statements

No Comments

No Known Activations