INDEX

Explanations

phrases related to discovering or investigating something, often involving a body

oai_token-act-pair · gpt-3.5-turbo

mentions of deceased individuals or references to bodies

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

arily

-0.76

 reperto

-0.66

yne

-0.64

ynes

-0.64

igue

-0.63

IQ

-0.63

venants

-0.63

ocations

-0.61

cms

-0.61

 embodiments

-0.61

POSITIVE LOGITS

gery

0.70

 Doctors

0.68

 Apostle

0.65

 Ideal

0.64

Sen

0.62

 Badge

0.62

 Hope

0.61

 Medic

0.59

 course

0.58

 Tail

0.58

Activations Density 0.295%

phrases related to discovering or investigating something, often involving a body

mentions of deceased individuals or references to bodies

No Comments

No Known Activations