INDEX

Explanations

words related to telescopes and observatories

oai_token-act-pair · gpt-3.5-turbo

references to telescopes and related observational tools

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

eem

-0.77

Interstitial

-0.76

estate

-0.74

death

-0.73

non

-0.71

edit

-0.71

no

-0.70

cit

-0.70

state

-0.69

ten

-0.69

POSITIVE LOGITS

 Telescope

1.32

 telescope

1.27

 telescopes

1.23

 astronomers

1.06

 microsc

0.99

 microscope

0.98

sonian

0.97

 astronomer

0.93

 Hubble

0.91

zo

0.90

Activations Density 0.017%

words related to telescopes and observatories

references to telescopes and related observational tools

No Known Activations