INDEX

Explanations

direct references to the reader using the word "You"

oai_token-act-pair · gpt-3.5-turbo

instances of 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wrapper

-0.63

itud

-0.62

 theirs

-0.60

 airs

-0.60

temp

-0.58

shore

-0.57

 majority

-0.56

 srfAttach

-0.55

ãĥ³ãĤ¸

-0.55

 stemming

-0.55

POSITIVE LOGITS

're

1.15

've

1.08

'll

1.02

Gov

1.00

 guessed

0.99

ngth

0.94

 Tube

0.94

imar

0.91

 guys

0.91

ths

0.90

Activations Density 0.108%

direct references to the reader using the word "You"

instances of the word "You."

No Comments

No Known Activations