INDEX

Explanations

mentions of illicit romantic relationships

oai_token-act-pair · gpt-3.5-turbo

phrases relating to situations characterized by having or experiencing

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

arning

-0.75

ensing

-0.71

NESS

-0.70

adj

-0.65

 Posts

-0.64

quartered

-0.64

available

-0.64

yond

-0.64

aware

-0.63

UC

-0.63

POSITIVE LOGITS

 meltdown

0.98

 chance

0.95

iphany

0.93

 intercourse

0.89

 conversation

0.88

 affair

0.86

 conversations

0.85

 dealings

0.85

 blast

0.84

 luck

0.84

Activations Density 0.212%

mentions of illicit romantic relationships

phrases relating to situations characterized by having or experiencing

No Comments

No Known Activations