INDEX

Explanations

references to the sports team "New England Patriots."

oai_token-act-pair · gpt-3.5-turbo

references to the New England Patriots football team

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

lasses

-0.85

undai

-0.80

osta

-0.74

yrinth

-0.73

 peas

-0.72

tips

-0.72

rowth

-0.70

spl

-0.67

orescence

-0.67

conservancy

-0.67

POSITIVE LOGITS

 Patriots

0.99

 Chiefs

0.75

ichick

0.75

 Mariners

0.74

 Jets

0.74

riots

0.73

 Belichick

0.72

 Amend

0.71

 Islanders

0.70

Bom

0.69

Activations Density 0.018%

references to the sports team "New England Patriots."

references to the New England Patriots football team

No Comments

No Known Activations