INDEX

Explanations

phrases related to where people live or resided

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "lived."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sonian

-0.87

essee

-0.82

enei

-0.75

elight

-0.74

ortium

-0.71

ociated

-0.71

aneers

-0.70

aligned

-0.70

reme

-0.69

uliffe

-0.69

POSITIVE LOGITS

lihood

0.89

 Wage

0.78

vic

0.73

liv

0.71

living

0.68

 living

0.68

 Reincarn

0.67

lier

0.66

 abroad

0.66

 Living

0.65

Activations Density 0.027%

phrases related to where people live or resided

occurrences of the word "lived."

No Comments

No Known Activations