INDEX

Explanations

phrases related to past events

oai_token-act-pair · gpt-3.5-turbo

references to time, specifically indicating past events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

cil

-0.68

aunders

-0.68

holes

-0.66

/#

-0.65

ordes

-0.63

olution

-0.62

death

-0.61

ongs

-0.61

CRE

-0.60

 Equality

-0.59

POSITIVE LOGITS

 month

1.18

 week

1.16

 year

1.05

 night

1.00

 semester

0.93

 summer

0.93

 Month

0.90

 ditch

0.90

 evening

0.87

 rites

0.86

Activations Density 0.059%

phrases related to past events

references to time, specifically indicating past events

No Comments

No Known Activations