INDEX

Explanations

political party names, particularly focusing on the Social Democrats

oai_token-act-pair · gpt-3.5-turbo

references to political parties, specifically Social Democrats and Liberal Democrats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Whitney

-0.75

 Nationwide

-0.72

inventoryQuantity

-0.72

 Dull

-0.68

 Webster

-0.67

FAA

-0.66

 McMahon

-0.64

 Garn

-0.63

depending

-0.63

 Compton

-0.63

POSITIVE LOGITS

alion

0.88

 Orchestra

0.79

 Syndicate

0.74

 rebels

0.74

astery

0.74

alions

0.73

 paramilitary

0.69

 Movement

0.69

ariat

0.69

ieties

0.67

Activations Density 0.072%

political party names, particularly focusing on the Social Democrats

references to political parties, specifically Social Democrats and Liberal Democrats

No Comments

No Known Activations