INDEX

Explanations

The neuron searches for references to legal documents and court proceedings

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "The."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.","

-0.73

Ïī

-0.72

rade

-0.71

dk

-0.70

Allows

-0.68

ÏĢ

-0.68

ãĥĺ

-0.67

Ò

-0.67

#$

-0.67

gpu

-0.66

POSITIVE LOGITS

odore

1.48

oret

1.47

resa

1.45

ories

1.29

 irony

1.19

 Problem

1.15

 downside

1.12

 Basics

1.09

 simplest

1.06

 Difference

1.05

Activations Density 0.426%

The neuron searches for references to legal documents and court proceedings

occurrences of the word "The."

No Comments

No Known Activations