INDEX

Explanations

phrases related to edits or revisions made to a text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "edit" in various contexts

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

milo

-0.83

gdala

-0.76

luster

-0.74

NetMessage

-0.71

merce

-0.70

ocket

-0.68

 pige

-0.67

emouth

-0.66

FTWARE

-0.66

ledged

-0.65

POSITIVE LOGITS

1.07

 edit

0.99

 summ

0.83

 edits

0.82

])

0.81

 spoiler

0.80

0.76

][

0.76

])

0.76

...]

0.74

Activations Density 0.013%

phrases related to edits or revisions made to a text

instances of the word "edit" in various contexts

No Comments

No Known Activations