INDEX

Explanations

instances where someone knows something or the concept of knowledge

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

amazon

-0.67

ksh

-0.67

 representing

-0.66

razil

-0.66

iffe

-0.64

zilla

-0.63

 owing

-0.62

Edit

-0.61

lette

-0.61

 suppose

-0.61

POSITIVE LOGITS

 extent

1.17

 basics

1.14

 exact

1.12

 same

1.10

 entirety

1.10

 difference

1.09

 entire

1.07

 slightest

1.06

 beginnings

1.04

oret

1.03

Activations Density 0.245%

instances where someone knows something or the concept of knowledge

No Comments

No Known Activations