INDEX

Explanations

statistical terms and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to statistical analysis and significance

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

lain

-1.11

shire

-0.90

eem

-0.89

aline

-0.83

nen

-0.80

xia

-0.75

eous

-0.74

amina

-0.74

ijing

-0.73

ryn

-0.72

POSITIVE LOGITS

istically

1.21

istical

1.06

 significance

0.98

 anomalies

0.96

 anomaly

0.89

 impossibility

0.88

 probability

0.85

istics

0.81

 probabilities

0.79

orically

0.77

Activations Density 0.017%

statistical terms and concepts

terms related to statistical analysis and significance

No Comments

No Known Activations