INDEX

Explanations

phrases related to instructions or commands

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "dos" and variations related to dosage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ISM

-0.96

Reviewer

-0.80

 Immunity

-0.73

gypt

-0.71

ICAN

-0.70

ocene

-0.70

INTON

-0.69

raud

-0.69

WB

-0.67

istically

-0.64

POSITIVE LOGITS

omething

1.29

dos

1.15

Dos

1.03

 Santos

1.01

hiba

0.98

wana

0.81

dos

0.80

pec

0.80

ega

0.79

ques

0.79

Activations Density 0.005%

phrases related to instructions or commands

occurrences of the word "dos" and variations related to dosage

No Comments

No Known Activations