INDEX

Explanations

words related to historical figures and events

oai_token-act-pair · gpt-3.5-turbo

proper nouns related to names and titles

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

 rollout

-0.88

 lasers

-0.86

 cybersecurity

-0.86

 analytics

-0.86

 targeting

-0.83

 ramps

-0.82

 NETWORK

-0.82

 Lyft

-0.82

 dashboard

-0.80

 transitioning

-0.78

POSITIVE LOGITS

anus

1.23

Ã»

1.13

onian

1.13

Ã¦

1.12

Ã¼

1.11

á¸

1.09

Ã¶n

1.02

ocrates

1.02

Åį

0.99

á¹

0.98

Activations Density 0.369%

words related to historical figures and events

proper nouns related to names and titles

No Comments

No Known Activations