INDEX

Explanations

addresses and locations in text

oai_token-act-pair · gpt-3.5-turbo

key details about locations and events, often focusing on building names and significant actions

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

 realise

-0.83

?".

-0.75

!".

-0.72

avour

-0.71

 organise

-0.70

 organisation

-0.67

 aluminium

-0.66

 Whilst

-0.66

 realised

-0.65

Firstly

-0.65

POSITIVE LOGITS

 Thursday

1.20

 Monday

1.19

 Wednesday

1.18

 Tuesday

1.17

 Friday

1.14

 Saturday

1.10

 beginning

1.09

 tomorrow

1.08

 Mondays

1.07

 Sept

1.03

Activations Density 0.750%

addresses and locations in text

key details about locations and events, often focusing on building names and significant actions

No Comments

No Known Activations