INDEX

Explanations

phrases indicating something is available or open for consideration or acquisition

oai_token-act-pair · gpt-3.5-turbo

phrases indicating items or topics that are available for consideration or debate

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

leigh

-0.73

raph

-0.71

urally

-0.67

ynes

-0.66

ILE

-0.65

ryu

-0.64

hiba

-0.64

 Ahead

-0.64

ashtra

-0.64

ipl

-0.63

POSITIVE LOGITS

 grabs

1.64

 sale

1.25

 renewal

1.04

 negotiation

1.01

 consideration

0.98

 inspection

0.97

 adoption

0.96

 auction

0.93

 pasture

0.91

 discussion

0.90

Activations Density 0.064%

phrases indicating something is available or open for consideration or acquisition

phrases indicating items or topics that are available for consideration or debate

No Comments

No Known Activations