INDEX

Explanations

mentions or descriptions of individuals

oai_token-act-pair · gpt-3.5-turbo

references to individuals or entities, particularly with the word "whose."

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

yi

-0.75

hal

-0.70

DT

-0.70

DI

-0.69

âĨ

-0.69

isp

-0.68

edd

-0.67

hari

-0.67

SPA

-0.67

PL

-0.67

POSITIVE LOGITS

 ancestors

1.04

own

1.03

 sole

0.98

 grandchildren

0.87

OWN

0.85

 parents

0.82

 predecessors

0.81

 namesake

0.81

 deepest

0.80

 fault

0.79

Activations Density 0.025%

mentions or descriptions of individuals

references to individuals or entities, particularly with the word "whose."

No Comments

No Known Activations