INDEX

Explanations

dates or time periods

oai_token-act-pair · gpt-3.5-turbo

references to time frames, specifically focusing on the concept of "the past."

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

 Franch

-0.80

lees

-0.71

 Dynamics

-0.67

hyde

-0.65

horn

-0.63

lee

-0.62

angelo

-0.61

ilda

-0.61

iquid

-0.61

addin

-0.61

POSITIVE LOGITS

decade

1.40

ebin

1.34

 millennium

1.15

 week

1.10

 month

1.09

 century

1.08

 fortnight

1.07

 year

1.02

 decades

1.01

 millennia

1.01

Activations Density 0.037%

dates or time periods

references to time frames, specifically focusing on the concept of "the past."

No Comments

No Known Activations