INDEX

Explanations

phrases or acronyms related to governmental or professional organizations

oai_token-act-pair · gpt-3.5-turbo

references to a specific entity or organization represented by "DA."

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

ties

-0.75

kies

-0.73

falls

-0.73

 Canaver

-0.72

sets

-0.70

ments

-0.69

packing

-0.69

lining

-0.68

naires

-0.68

deck

-0.67

POSITIVE LOGITS

ILY

1.24

BLE

1.10

VID

1.10

VIS

0.99

OTA

0.92

roid

0.87

ZZ

0.86

WN

0.85

ption

0.84

VE

0.82

Activations Density 0.014%

phrases or acronyms related to governmental or professional organizations

references to a specific entity or organization represented by "DA."

No Comments

No Known Activations