INDEX

Explanations

instances of numbers followed by punctuation

oai_token-act-pair · gpt-3.5-turbo

numbers and numerical expressions in the text

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

 elevation

-0.74

 padd

-0.73

 swallowing

-0.71

 guarding

-0.71

 travers

-0.70

 pastoral

-0.68

 brid

-0.68

 brav

-0.67

hung

-0.67

 whipping

-0.65

POSITIVE LOGITS

 SHARES

1.01

NCT

0.86

maxwell

0.80

ertodd

0.80

 Â·

0.76

rd

0.75

nd

0.75

 Facts

0.74

 Expand

0.73

:{

0.73

Activations Density 0.099%

instances of numbers followed by punctuation

numbers and numerical expressions in the text

No Comments

No Known Activations