INDEX

Explanations

mentions of actions taken by people in various situations, such as being arrested, receiving compliments, reading articles, and expressing displeasure

oai_token-act-pair · gpt-3.5-turbo

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

$.

-0.66

%.

-0.59

};

-0.59

;}

-0.55

_.

-0.55

+.

-0.54

}.

-0.54

%;

-0.53

.;

-0.51

.</

-0.51

POSITIVE LOGITS

 regarding

0.79

osponsors

0.77

 lately

0.74

 nowadays

0.71

 relating

0.66

ento

0.66

 here

0.62

 herein

0.62

 Regarding

0.62

buquerque

0.61

Activations Density 0.902%

mentions of actions taken by people in various situations, such as being arrested, receiving compliments, reading articles, and expressing displeasure

No Comments

No Known Activations