INDEX

Explanations

words related to requesting, asking for, or seeking assistance or information

oai_token-act-pair · gpt-3.5-turbo

terms related to requests for donations or contributions

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

Aqu

-0.77

bur

-0.69

wreck

-0.68

 Yard

-0.67

fall

-0.65

mk

-0.64

 Underground

-0.63

board

-0.63

breaks

-0.63

este

-0.62

POSITIVE LOGITS

 solicit

1.28

 solicitation

1.18

 solic

1.15

 bids

0.90

olicited

0.85

itta

0.84

ORS

0.77

yip

0.74

 invitations

0.74

 bribes

0.73

Activations Density 0.030%

words related to requesting, asking for, or seeking assistance or information

terms related to requests for donations or contributions

No Comments

No Known Activations