INDEX

Explanations

statistical terms

oai_token-act-pair · gpt-3.5-turbo

references to statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

hips

-0.73

cuts

-0.71

 Talks

-0.67

original

-0.66

 bends

-0.63

 Original

-0.61

 Company

-0.61

 listens

-0.60

[_

-0.60

 Dinner

-0.60

POSITIVE LOGITS

 statistic

4.02

 statistics

2.15

Statistics

1.82

 Statistics

1.76

 statistical

1.72

 Statistical

1.47

 stats

1.46

 stat

1.37

Stat

1.34

stat

1.31

Activations Density 0.015%

statistical terms

references to statistics

No Comments

No Known Activations