INDEX

Explanations

dates and locations mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "on" in various contexts, particularly related to time and location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

aram

-0.75

ingham

-0.72

AMA

-0.72

ographers

-0.66

arth

-0.65

ographically

-0.65

abis

-0.63

negie

-0.63

plin

-0.63

amus

-0.63

POSITIVE LOGITS

 Wednesday

1.41

 Saturday

1.39

 Thursday

1.39

 Tuesday

1.37

Feb

1.37

 Friday

1.36

 Sunday

1.34

 Monday

1.34

 Sept

1.33

 July

1.31

Activations Density 0.106%

dates and locations mentioned in the text

occurrences of the word "on" in various contexts, particularly related to time and location

No Comments

No Known Activations