INDEX

Explanations

names or titles associated with academic degrees

oai_token-act-pair · gpt-3.5-turbo

references to academic degrees, particularly doctoral qualifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ¨ãĥ«

-0.77

DragonMagazine

-0.76

éĹĺ

-0.72

 ashes

-0.69

âĹ¼

-0.67

shi

-0.65

bum

-0.65

 folders

-0.64

ãĥ¼ãĥ³

-0.62

 lookout

-0.62

POSITIVE LOGITS

MPH

0.91

 specializing

0.87

estinal

0.83

 Candidate

0.79

rint

0.77

heses

0.76

Ħ¢

0.75

 Veter

0.75

aceutical

0.75

sych

0.74

Activations Density 0.045%

names or titles associated with academic degrees

references to academic degrees, particularly doctoral qualifications

No Comments

No Known Activations