INDEX

Explanations

phrases and clauses that denote conclusions or transitions in thought

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

"That" followed by "said"

np_acts-logits-general · gemini-2.0-flash

that said

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

 propOrder

-0.58

ⓧ

-0.54

 &___

-0.54

Tikang

-0.52

MessageTagHelper

-0.50

 оригіналу

-0.48

 Biôgrafia

-0.48

 kasarigan

-0.48

 AssemblyCulture

-0.47

цездатний

-0.45

POSITIVE LOGITS

 said

1.66

said

1.22

Said

1.14

 gesagt

1.08

Having

1.08

 saying

1.05

 SAID

1.05

 Having

1.04

 gezegd

1.03

 having

1.02

Activations Density 0.208%

phrases and clauses that denote conclusions or transitions in thought

"That" followed by "said"

that said

No Comments

No Known Activations