INDEX

Explanations

The main thing this neuron does is find names related to specific individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific names, particularly "Wade" and "Chen."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

é¾įå

-0.81

gio

-0.73

ļ

-0.73

Ľ

-0.72

adelphia

-0.71

phant

-0.71

ariat

-0.70

asury

-0.70

ī

-0.70

orie

-0.70

POSITIVE LOGITS

nesday

0.87

 Wink

0.78

 Bauer

0.78

 Wade

0.74

erers

0.67

 Spin

0.66

arella

0.66

abase

0.66

Pixel

0.62

 Warm

0.61

Activations Density 0.058%

The main thing this neuron does is find names related to specific individuals

references to specific names, particularly "Wade" and "Chen."

No Comments

No Known Activations