INDEX

Explanations

locations where individuals arrive

oai_token-act-pair · gpt-3.5-turbo

references to locations and significant places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Goo

-0.66

]}

-0.64

 Fact

-0.59

 Away

-0.58

 Remain

-0.57

 Meter

-0.56

 Extrem

-0.56

]);

-0.56

 Wrap

-0.55

%.

-0.55

POSITIVE LOGITS

 expecting

1.04

 intending

0.95

 unprepared

0.93

 unexpectedly

0.91

 willingly

0.90

 smelling

0.90

 voluntarily

0.88

 dressed

0.87

 clad

0.86

 seeking

0.86

Activations Density 0.399%

locations where individuals arrive

references to locations and significant places

No Comments

No Known Activations