INDEX

Explanations

phrases related to a specific keyword "att"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "att" and its variations in various contexts

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

 Galile

-0.70

 Britann

-0.69

 fentanyl

-0.66

BuyableInstoreAndOnline

-0.65

 Bind

-0.65

UGE

-0.64

AAF

-0.63

 methyl

-0.62

 Uzbek

-0.60

lda

-0.60

POSITIVE LOGITS

anooga

1.43

ributes

1.25

itude

1.23

ributed

1.20

achment

1.13

leground

1.12

ainment

1.11

ety

1.10

idy

1.03

iston

1.00

Activations Density 0.014%

phrases related to a specific keyword "att"

occurrences of the word "att" and its variations in various contexts

No Comments

No Known Activations