INDEX

Explanations

phrases related to future events

oai_token-act-pair · gpt-3.5-turbo

references to timeframes and upcoming events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ional

-0.74

ames

-0.68

iott

-0.66

ivas

-0.65

Reason

-0.63

itiz

-0.62

ectomy

-0.61

iva

-0.60

\'

-0.60

quit

-0.60

POSITIVE LOGITS

 meantime

1.60

 midst

1.12

 guise

1.09

 aftermath

1.09

 ensuing

1.07

 evenings

1.06

 intervening

1.06

 vicinity

1.05

 wake

1.03

 mornings

1.00

Activations Density 0.219%

phrases related to future events

references to timeframes and upcoming events

No Comments

No Known Activations