INDEX

Explanations

conditional statements and expressions of desire or intent

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

hypothetical `could` or `would`

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

featureID

-0.85

 AssemblyTitle

-0.68

 Infórmanos

-0.66

rungsseite

-0.64

 AssemblyCompany

-0.63

 increí

-0.61

 informée

-0.60

AndEndTag

-0.60

HostException

-0.59

 Infór

-0.58

POSITIVE LOGITS

 betweenstory

0.42

加

0.38

倒

0.38

pre

0.36

事

0.36

fog

0.35

McG

0.35

WriteLiteral

0.35

Est

0.34

 Gruber

0.33

Activations Density 0.167%

conditional statements and expressions of desire or intent

hypothetical `could` or `would`

No Comments

No Known Activations