INDEX

Explanations

phrases mentioning specific things like subjects, headlines, and titles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "the."

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

rontal

-0.83

itism

-0.71

vere

-0.68

oka

-0.67

uristic

-0.67

heit

-0.67

hol

-0.67

alach

-0.66

lege

-0.66

ulence

-0.65

POSITIVE LOGITS

 midst

1.20

 context

1.10

 aforementioned

1.04

 meantime

1.02

 vicinity

0.99

 aftermath

0.99

 article

0.96

 preceding

0.96

 absence

0.92

 comments

0.91

Activations Density 0.212%

phrases mentioning specific things like subjects, headlines, and titles

instances of the word "the."

No Comments

No Known Activations