INDEX

Explanations

mentions of eligibility criteria or requirements

oai_token-act-pair · gpt-3.5-turbo

references to eligibility criteria 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

âķĲâķĲ

-0.77

tons

-0.69

EMS

-0.69

Pic

-0.67

hed

-0.66

hen

-0.64

 antioxid

-0.63

 beating

-0.62

vard

-0.62

ERC

-0.62

POSITIVE LOGITS

 eligibility

1.24

 criteria

1.00

 qualifications

0.87

 clearance

0.83

 criterion

0.82

ibility

0.79

 disqualified

0.78

 requirements

0.78

 ineligible

0.78

acies

0.77

Activations Density 0.011%

mentions of eligibility criteria or requirements

references to eligibility criteria in various contexts

No Comments

No Known Activations