INDEX

Explanations

mentions of city names

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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uckland

-1.07

igham

-0.96

etsk

-0.90

aye

-0.90

pmwiki

-0.87

iotic

-0.84

byter

-0.83

ivia

-0.82

ibilities

-0.82

ulously

-0.82

POSITIVE LOGITS

 Council

1.07

scape

1.02

wide

0.99

 Limits

0.93

 Attorney

0.88

 Halls

0.87

 Auditor

0.86

 Paper

0.85

 Directive

0.83

 Nights

0.81

Activations Density 0.022%

mentions of city names

mentions of specific cities

No Comments

No Known Activations