INDEX

Explanations

instances of the word "was," indicating a focus on past-tense descriptions or states

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

expressing a past thought

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

WriteBarrier

-0.55

RenderAtEndOf

-0.54

ModelAdmin

-0.52

 CURIAM

-0.50

 EClass

-0.50

 BoxFit

-0.50

bewerken

-0.49

PMailer

-0.48

 fraî

-0.48

principalColumn

-0.48

POSITIVE LOGITS

possibly

0.47

 maybe

0.46

 possibly

0.43

maybe

0.43

Possibly

0.42

0.40

是不是

0.40

Maybe

0.40

really

0.40

 probably

0.39

Activations Density 0.068%

instances of the word "was," indicating a focus on past-tense descriptions or states

expressing a past thought

No Comments

No Known Activations

instances of the word "was," indicating a focus on past-tense descriptions or states

expressing a past thought

No Comments

No Known Activations