INDEX

Explanations

references to reviews or examinations being conducted or completed

oai_token-act-pair · gpt-3.5-turbo

terms associated with reviews and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Notable

-0.69

Registered

-0.67

cakes

-0.66

absolute

-0.64

NAME

-0.64

 Solitaire

-0.62

 Strongh

-0.62

Favorite

-0.61

Ys

-0.60

Christmas

-0.60

POSITIVE LOGITS

 undertaken

1.12

 conducted

1.09

 process

1.08

 examining

0.95

opian

0.90

 commissioned

0.87

 underway

0.86

andum

0.84

 examination

0.83

 assessing

0.83

Activations Density 0.137%

references to reviews or examinations being conducted or completed

terms associated with reviews and evaluations

No Comments

No Known Activations