INDEX

Explanations

terms related to statistical sampling and confidence levels

oai_token-act-pair · gpt-3.5-turbo

References to statistical margin of error and confidence levels in survey data

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

psey

-0.83

gars

-0.82

christ

-0.79

enhagen

-0.78

fman

-0.77

sov

-0.76

geist

-0.76

ndum

-0.75

bable

-0.74

imer

-0.73

POSITIVE LOGITS

{*

0.79

Duration

0.76

 Comcast

0.73

 Beginning

0.73

 USPS

0.72

 EVENTS

0.70

 Residents

0.67

 Raise

0.67

 applicable

0.67

 Seller

0.66

Activations Density 0.041%

terms related to statistical sampling and confidence levels

References to statistical margin of error and confidence levels in survey data

No Comments

No Known Activations