INDEX

Explanations

words related to drugs or substances

oai_token-act-pair · gpt-3.5-turbo

the abbreviation "dr" and related variations

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

 Corpus

-0.94

eers

-0.87

SHIP

-0.79

eering

-0.75

ISM

-0.72

yip

-0.72

ERN

-0.72

eer

-0.69

 Pose

-0.68

TING

-0.64

POSITIVE LOGITS

agons

1.16

inking

1.11

unk

1.10

unks

1.09

ifts

1.08

inks

1.05

inker

1.04

iller

1.03

aco

1.02

ink

1.01

Activations Density 0.023%

words related to drugs or substances

the abbreviation "dr" and related variations

No Comments

No Known Activations