INDEX

Explanations

references to individuals as "suspects" in legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ContentLoaded

-0.58

gdx

-0.55

 跳转至

-0.55

 învă

-0.50

 anglès

-0.48

ecore

-0.47

ChromeDriver

-0.47

PreferredItem

-0.47

RegistryLite

-0.46

laken

-0.46

POSITIVE LOGITS

 suspect

4.56

 suspects

3.91

 suspected

3.09

 suspicion

2.89

 suspe

2.81

 sospe

2.69

Sus

2.55

sus

2.53

 suspicions

2.44

Sus

2.40

Activations Density 0.092%

references to individuals as "suspects" in legal contexts

No Comments

No Known Activations

references to individuals as "suspects" in legal contexts

No Comments

No Known Activations