INDEX

Explanations

mentions of the word "Qu" followed by a digit (potentially part of the word Quilt)

oai_token-act-pair · gpt-3.5-turbo

references to the concept of 'Quorum.'

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

HAEL

-0.76

AGES

-0.75

 buds

-0.69

 deed

-0.67

ãĤ¹ãĥĪ

-0.64

 controller

-0.63

ãģĨ

-0.63

 haze

-0.62

 controllers

-0.62

 warming

-0.62

POSITIVE LOGITS

arantine

1.19

ests

1.07

ois

1.05

oted

1.04

atro

0.99

oting

0.99

icks

0.98

ipped

0.96

artz

0.96

isition

0.96

Activations Density 0.015%

mentions of the word "Qu" followed by a digit (potentially part of the word Quilt)

references to the concept of 'Quorum.'

No Comments

No Known Activations