INDEX

Explanations

quotations within text

oai_token-act-pair · gpt-3.5-turbo

quotes or phrases attributed to individuals or sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Izan

-0.79

Ern

-0.76

 viewers

-0.76

 Elements

-0.76

 wrinkles

-0.76

 Asians

-0.75

 blockers

-0.73

 bows

-0.73

IDs

-0.72

 Blacks

-0.72

POSITIVE LOGITS

very

1.23

complete

1.18

classic

1.17

highly

1.16

few

1.13

healthy

1.13

significant

1.12

reasonable

1.12

technical

1.10

little

1.09

Activations Density 0.035%

quotations within text

quotes or phrases attributed to individuals or sources

No Comments

No Known Activations