INDEX

Explanations

proper nouns or specific names

oai_token-act-pair · gpt-3.5-turbo

sections of text that appear to relate to timelines or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 traveling

-0.83

 tremend

-0.79

 maneuver

-0.77

 favors

-0.74

 traveled

-0.74

 favored

-0.74

 favoring

-0.72

 travelers

-0.71

 maneu

-0.71

 utilized

-0.70

POSITIVE LOGITS

Labour

1.21

Â£

1.01

Britain

1.00

Austral

1.00

Liverpool

1.00

Scotland

0.99

BBC

0.95

England

0.95

Ireland

0.95

Firstly

0.92

Activations Density 0.410%

proper nouns or specific names

sections of text that appear to relate to timelines or numerical data

No Comments

No Known Activations