INDEX

Explanations

phrases related to the interconnectedness or interdependence of different entities

oai_token-act-pair · gpt-3.5-turbo

references to relationships or interactions between two entities or parties

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

ogle

-0.72

umper

-0.63

mson

-0.59

\<

-0.57

stad

-0.56

ervation

-0.56

opathy

-0.55

{*

-0.55

duc

-0.55

teness

-0.54

POSITIVE LOGITS

 respectively

1.89

 together

1.80

 mutually

1.73

 alike

1.68

 jointly

1.65

together

1.63

 Together

1.61

 interchange

1.48

 toget

1.38

Together

1.33

Activations Density 1.461%

phrases related to the interconnectedness or interdependence of different entities

references to relationships or interactions between two entities or parties

No Comments

No Known Activations