INDEX

Explanations

references to individuals named "Doug."

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Doug."

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

Negative Logits

kaya

-0.74

*/(

-0.72

mberg

-0.72

istic

-0.71

iferation

-0.70

culosis

-0.69

CVE

-0.68

Interstitial

-0.68

 Tend

-0.67

istical

-0.66

POSITIVE LOGITS

herty

1.54

ards

1.03

aneers

0.87

Ell

0.87

arded

0.86

 Doug

0.84

Fir

0.81

 Matthews

0.81

ords

0.81

ARDS

0.80

Activations Density 0.014%

references to individuals named "Doug."

repeated mentions of the name "Doug."

No Known Activations