INDEX

Explanations

medical procedures and scientific terms

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific and technical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 characteristic

-0.77

 utmost

-0.70

},"

-0.67

DragonMagazine

-0.67

BuyableInstoreAndOnline

-0.65

 absence

-0.64

 resemblance

-0.64

 Tsukuyomi

-0.64

 unavoid

-0.62

 Victory

-0.60

POSITIVE LOGITS

ciating

1.08

imating

1.07

izes

1.07

ulating

1.07

ify

1.04

ouncing

1.02

ifies

1.02

izing

1.02

posing

0.98

asting

0.97

Activations Density 0.446%

medical procedures and scientific terms

terms related to scientific and technical concepts

No Comments

No Known Activations