INDEX

Explanations

phrases related to making decisions or taking actions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.71

raught

-0.69

²¾

-0.68

oubted

-0.65

ritional

-0.64

oubt

-0.64

tnc

-0.62

rocal

-0.61

 actionGroup

-0.61

ounter

-0.60

POSITIVE LOGITS

 goddamn

1.41

*.

1.18

1.17

!!!

1.17

 damn

1.16

 godd

1.14

 fucking

1.14

!!!!!!!!

1.11

!!!!

1.11

!!!!!

1.10

Activations Density 1.008%

phrases related to making decisions or taking actions

No Comments

No Known Activations