INDEX

Explanations

proper names associated with the name "Hassan."

oai_token-act-pair · gpt-3.5-turbo

the name "Hassan" and its variations, indicating a focus on individuals with that name

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

FORE

-0.75

fare

-0.72

BuyableInstoreAndOnline

-0.72

idge

-0.67

LOAD

-0.67

BY

-0.66

AU

-0.65

OTT

-0.65

PF

-0.63

lying

-0.62

POSITIVE LOGITS

 Rouhani

1.17

 Hassan

1.06

etics

0.94

daq

0.93

emaker

0.89

ascus

0.86

 Whites

0.83

azi

0.81

emet

0.80

atos

0.80

Activations Density 0.014%

proper names associated with the name "Hassan."

the name "Hassan" and its variations, indicating a focus on individuals with that name

No Comments

No Known Activations