INDEX

Explanations

instances of the word "received"

oai_token-act-pair · gpt-3.5-turbo

phrases indicating that something has been received

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

 Quantity

-0.64

fall

-0.60

flation

-0.58

isting

-0.56

 fallacy

-0.56

hole

-0.55

ouf

-0.54

 Madness

-0.53

 obsc

-0.53

olini

-0.53

POSITIVE LOGITS

DragonMagazine

0.91

dinand

0.88

sbm

0.82

terson

0.81

imental

0.78

andom

0.77

namese

0.77

ILY

0.76

soever

0.75

å¼

0.73

Activations Density 0.036%

instances of the word "received"

phrases indicating that something has been received

No Comments

No Known Activations