INDEX

Explanations

mentions of decades by their numerals followed by the letter 's'

oai_token-act-pair · gpt-3.5-turbo

references to specific decades

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

edIn

-0.79

Maker

-0.70

Tickets

-0.63

license

-0.62

DERR

-0.62

 Strongh

-0.61

anan

-0.61

 Maker

-0.60

acts

-0.60

access

-0.60

POSITIVE LOGITS

 onwards

1.12

 onward

1.10

era

1.01

ixties

1.00

-'

0.97

Era

0.86

hey

0.86

 century

0.81

decade

0.79

 nostalg

0.79

Activations Density 0.078%

mentions of decades by their numerals followed by the letter 's'

references to specific decades

No Comments

No Known Activations