INDEX

Explanations

words related to hotels and accommodations

oai_token-act-pair · gpt-3.5-turbo

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

 Nile

-0.66

ques

-0.63

ted

-0.62

gencies

-0.62

lda

-0.61

ngth

-0.59

 caution

-0.58

Alz

-0.58

govtrack

-0.58

bered

-0.58

POSITIVE LOGITS

ipeg

1.68

ovation

1.36

ikuman

1.28

osuke

1.24

spir

1.23

ocent

1.22

itus

1.12

igan

1.11

ett

1.05

ings

1.03

Activations Density 0.040%

words related to hotels and accommodations

No Comments

No Known Activations