INDEX

Explanations

words related to the city or location of Toronto

oai_token-act-pair · gpt-3.5-turbo

references to the city of Toronto

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

 Laos

-0.74

SPONSORED

-0.73

urdue

-0.72

heit

-0.71

ateurs

-0.66

abase

-0.66

 forgiveness

-0.63

acebook

-0.61

 veterin

-0.60

 inval

-0.59

POSITIVE LOGITS

ondo

0.77

ooth

0.75

Ped

0.70

 Janeiro

0.70

onto

0.69

IDS

0.69

Ïī

0.69

idis

0.66

undo

0.66

iden

0.65

Activations Density 0.147%

words related to the city or location of Toronto

references to the city of Toronto

No Comments

No Known Activations