INDEX

Explanations

short phrases indicating instructions or conditions

oai_token-act-pair · gpt-3.5-turbo

phrases that reference the reader's identity or experience

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

"},

-0.84

NetMessage

-0.69

 Amendments

-0.68

APP

-0.67

Eag

-0.65

ð

-0.64

rocal

-0.62

VERTISEMENT

-0.61

WOR

-0.60

Ham

-0.60

POSITIVE LOGITS

 inclined

0.84

 lucky

0.83

 unsure

0.82

 unlucky

0.73

 undecided

0.72

 yourself

0.71

 interested

0.71

 subscribed

0.69

 calibr

0.69

 wondering

0.68

Activations Density 0.138%

short phrases indicating instructions or conditions

phrases that reference the reader's identity or experience

No Comments

No Known Activations