INDEX

Explanations

mentions of the name "Dwight"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Dwight" and its variations in various contexts

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

busters

-0.74

tale

-0.74

mented

-0.72

phies

-0.72

otech

-0.71

gra

-0.71

chant

-0.71

culosis

-0.70

smanship

-0.70

lia

-0.69

POSITIVE LOGITS

 ILCS

0.78

 Shooter

0.76

oleon

0.72

 Hots

0.72

éĹĺ

0.69

 Schr

0.69

 Peninsula

0.67

ackers

0.66

 peninsula

0.66

EED

0.66

Activations Density 0.040%

mentions of the name "Dwight"

references to the name "Dwight" and its variations in various contexts

No Comments

No Known Activations