INDEX

Explanations

mentions of specific locations

oai_token-act-pair · gpt-3.5-turbo

references to museums and their exhibits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Lyft

-1.05

 Comcast

-0.87

ISP

-0.82

 thrott

-0.81

 throttle

-0.80

 ISPs

-0.78

 caffeine

-0.76

 latency

-0.75

 DHCP

-0.74

 timeout

-0.72

POSITIVE LOGITS

 archaeological

1.33

 Archae

1.21

 archaeologists

1.19

 archae

1.11

 sculptures

1.10

 excavation

1.09

 excav

1.09

artifacts

1.08

 museum

1.07

 Photograph

1.01

Activations Density 0.694%

mentions of specific locations

references to museums and their exhibits

No Comments

No Known Activations