INDEX

Explanations

mentions of the city of Portland

oai_token-act-pair · gpt-3.5-turbo

references to the city of Portland and its associated sports teams

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ktop

-0.77

maid

-0.76

vana

-0.73

graded

-0.73

grading

-0.70

terday

-0.69

ãĤ¼ãĤ¦ãĤ¹

-0.67

egal

-0.67

iour

-0.67

 sclerosis

-0.66

POSITIVE LOGITS

 Timbers

1.12

ers

0.94

icut

0.91

shire

0.86

 Oregon

0.78

hurst

0.78

 Harbor

0.77

sylvania

0.73

Portland

0.73

 Trail

0.73

Activations Density 0.022%

mentions of the city of Portland

references to the city of Portland and its associated sports teams

No Comments

No Known Activations