INDEX

Explanations

references to a specific individual named Az

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Aziz."

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

dfx

-0.77

ACTED

-0.76

aceous

-0.73

mercial

-0.70

nesday

-0.70

çīĪ

-0.69

 Norn

-0.67

CLASSIFIED

-0.66

 externalToEVAOnly

-0.66

 Fargo

-0.65

POSITIVE LOGITS

azel

1.10

tec

1.01

eri

0.99

Az

0.91

Az

0.90

qu

0.88

uma

0.87

iph

0.87

iol

0.86

iz

0.85

Activations Density 0.012%

references to a specific individual named Az

mentions of the name "Aziz."

No Comments

No Known Activations