INDEX

Explanations

terms related to imprisonment and incarceration

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

afficheront

-0.90

 propOrder

-0.89

 surla

-0.88

 Seeder

-0.85

WebElementEntity

-0.85

 resourceCulture

-0.84

AnchorTagHelper

-0.81

évaluateur

-0.81

 Infórmanos

-0.80

principalTable

-0.80

POSITIVE LOGITS

 prison

1.94

 jail

1.85

Prison

1.77

 Prison

1.75

prison

1.73

 Jail

1.60

 prisons

1.60

 PRISON

1.57

 prisoners

1.53

 prisoner

1.49

Activations Density 0.273%

terms related to imprisonment and incarceration

No Comments

No Known Activations