INDEX

Explanations

descriptions of products and their features

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the availability or presentation of products

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

benef

-0.67

maxwell

-0.67

 Valley

-0.67

eur

-0.62

 Writers

-0.61

laus

-0.60

pedia

-0.60

orthodox

-0.60

eering

-0.59

oris

-0.59

POSITIVE LOGITS

 equipped

1.27

 packaged

1.16

 bundled

1.08

equipped

0.97

 loaded

0.92

 stocked

0.92

 furnished

0.92

 fitted

0.91

 packed

0.89

 primed

0.87

Activations Density 0.064%

descriptions of products and their features

phrases indicating the availability or presentation of products

No Comments

No Known Activations