INDEX

Explanations

personal pronouns followed by verbs

oai_token-act-pair · gpt-3.5-turbo

the word "You."

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

 srfAttach

-0.64

Lago

-0.62

shore

-0.60

 ammon

-0.59

ensable

-0.58

 stemming

-0.58

ice

-0.58

icy

-0.57

actic

-0.57

ipal

-0.57

POSITIVE LOGITS

're

1.38

've

1.21

'll

1.19

 guys

1.06

'd

0.97

tub

0.96

ths

0.88

ldon

0.87

ngth

0.85

 know

0.84

Activations Density 0.104%

personal pronouns followed by verbs

the word "You."

No Comments

No Known Activations