INDEX

Explanations

separate mentions of the term "IP" within the text

oai_token-act-pair · gpt-3.5-turbo

instances of the term "pip" and related phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 EntityItem

-0.90

DERR

-0.77

 Dying

-0.76

ufact

-0.73

DEV

-0.73

é¾

-0.73

 withd

-0.70

BIP

-0.66

 Commodore

-0.65

soDeliveryDate

-0.65

POSITIVE LOGITS

artisan

1.32

otent

1.28

osit

1.18

ublic

1.04

olitan

1.04

resent

1.04

etition

1.02

arent

0.99

olitics

0.99

uls

0.97

Activations Density 0.052%

separate mentions of the term "IP" within the text

instances of the term "pip" and related phrases

No Comments

No Known Activations