INDEX

Explanations

instances of the word "in."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.66

 nailed

-0.64

 spoil

-0.58

 babe

-0.57

 undone

-0.56

 bandwagon

-0.56

 lodged

-0.55

 endors

-0.55

pim

-0.54

 combatants

-0.54

POSITIVE LOGITS

 lieu

1.41

 addition

1.31

 spite

1.31

 accordance

1.26

 order

1.15

clus

1.15

 conjunction

1.14

iti

1.09

jured

1.08

flation

1.08

Activations Density 0.210%

instances of the word "in."

occurrences of the word "in"

No Comments

No Known Activations