INDEX

Explanations

qualifications or instances of being qualified

oai_token-act-pair · gpt-3.5-turbo

terms related to qualifications or being qualified for roles or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 DRAG

-0.75

âĸ¬

-0.73

 drip

-0.68

 Sparrow

-0.67

corn

-0.67

 Lans

-0.65

 Spiegel

-0.65

 Gardens

-0.65

 Spice

-0.64

ectar

-0.64

POSITIVE LOGITS

 qualifications

0.90

 applicants

0.85

ifiers

0.85

 qualified

0.84

dinand

0.84

qualified

0.83

ifications

0.82

ifies

0.81

ifying

0.81

 qualification

0.81

Activations Density 0.013%

qualifications or instances of being qualified

terms related to qualifications or being qualified for roles or positions

No Comments

No Known Activations