INDEX

Explanations

numerical figures with a comma included

oai_token-act-pair · gpt-3.5-turbo

comma-separated numerical data or statistics

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

ngth

-0.74

enhagen

-0.59

 traveller

-0.57

 beauty

-0.57

 stre

-0.56

swick

-0.54

 maiden

-0.53

Bos

-0.53

 Brill

-0.53

amate

-0.51

POSITIVE LOGITS

1.22

1.19

1.14

1.13

1.08

1.03

1.02

1.01

1.00

0.99

Activations Density 0.076%

numerical figures with a comma included

comma-separated numerical data or statistics

No Comments

No Known Activations