INDEX

Explanations

mentions of specific cities, particularly focusing on urban contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of specific cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

etsk

-0.99

uckland

-0.98

igham

-0.93

iotic

-0.93

aye

-0.88

ulously

-0.88

iosis

-0.85

ibilities

-0.85

iscopal

-0.82

encer

-0.82

POSITIVE LOGITS

 Council

1.07

wide

1.07

scape

0.99

 Halls

0.88

 Limits

0.88

 Nights

0.87

 Islanders

0.86

 Attorney

0.84

 Hall

0.83

 Auditor

0.81

Activations Density 0.026%

mentions of specific cities, particularly focusing on urban contexts

mentions of specific cities

No Comments

No Known Activations