INDEX

Explanations

phrases or words indicating purpose or rationale in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

principalColumn

-0.55

 GenerationType

-0.52

 propOrder

-0.52

ScopeManager

-0.51

 therefor

-0.50

 Baillargeon

-0.49

 pourtant

-0.48

 addirittura

-0.48

šinou

-0.47

 مشين

-0.47

POSITIVE LOGITS

 convenience

1.32

 ease

1.25

 clarity

1.24

 easier

1.24

 simplicity

1.20

easier

1.17

Easier

1.02

 readability

1.00

convenience

0.99

 Easier

0.99

Activations Density 0.557%

phrases or words indicating purpose or rationale in a context

No Comments

No Known Activations