INDEX

Explanations

mentions of socialist ideology or related terms

oai_token-act-pair · gpt-3.5-turbo

references to socialism or socialist concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aunder

-0.80

rawdownloadcloneembedreportprint

-0.75

shown

-0.73

igree

-0.71

 Kinnikuman

-0.71

 Dull

-0.68

upon

-0.68

inventoryQuantity

-0.67

 MacArthur

-0.66

asso

-0.65

POSITIVE LOGITS

 socialist

0.93

 socialism

0.89

 socialists

0.88

 paradise

0.80

 Socialist

0.75

 Socialism

0.74

 dictatorship

0.71

 egalitarian

0.70

 democratic

0.70

 republic

0.69

Activations Density 0.010%

mentions of socialist ideology or related terms

references to socialism or socialist concepts

No Comments

No Known Activations