INDEX

Explanations

quotations

oai_token-act-pair · gpt-3.5-turbo

quoted speech or dialogue in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Alger

-0.70

 derby

-0.70

 affiliate

-0.68

 childbirth

-0.68

 Gibson

-0.66

 Stam

-0.66

 photography

-0.65

 Garry

-0.65

 bows

-0.65

 vanity

-0.65

POSITIVE LOGITS

absolutely

1.11

extremely

1.11

probably

1.10

almost

1.09

completely

1.09

highly

1.07

moderate

1.07

neutral

1.07

whose

1.06

Mr

1.05

Activations Density 0.132%

quotations

quoted speech or dialogue in the text

No Comments

No Known Activations