INDEX

Explanations

sentences ending with a full stop and with a high amount of certainty or decisiveness

oai_token-act-pair · gpt-3.5-turbo

sentences that express uncertainty or questions about understanding and social dynamics

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

 upgr

-0.73

 unden

-0.72

 landfall

-0.68

 panc

-0.68

 mammoth

-0.68

ernaut

-0.68

 exclusively

-0.68

 sequential

-0.68

 untouched

-0.67

 sustained

-0.66

POSITIVE LOGITS

 Especially

1.20

 Usually

1.17

 Regardless

1.17

 They

1.17

 Often

1.15

 Their

1.15

 Particularly

1.13

 Examples

1.12

 Flavoring

1.11

 Whether

1.10

Activations Density 0.750%

sentences ending with a full stop and with a high amount of certainty or decisiveness

sentences that express uncertainty or questions about understanding and social dynamics

No Comments

No Known Activations