INDEX

Explanations

instances of ordinal numbers or rankings indicated by "No." with a numerical value following it

oai_token-act-pair · gpt-3.5-turbo

numerical rankings or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

gypt

-0.75

ãĥ¼ãĥĨ

-0.73

imar

-0.70

ande

-0.69

 herds

-0.67

peria

-0.67

irez

-0.64

itaire

-0.64

ãĥį

-0.63

lag

-0.63

POSITIVE LOGITS

CLASSIFIED

0.81

Ops

0.68

DIV

0.67

 Ranking

0.66

McC

0.66

eous

0.66

jpg

0.65

Recommend

0.65

0.64

 Priority

0.63

Activations Density 0.023%

instances of ordinal numbers or rankings indicated by "No." with a numerical value following it

numerical rankings or positions

No Comments

No Known Activations