INDEX

Explanations

instances of the word "included"

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "in" alongside associated contexts or categories

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

JJ

-0.67

gging

-0.65

gged

-0.64

iger

-0.64

fficient

-0.61

ishi

-0.60

KK

-0.60

psi

-0.58

ÅĤ

-0.58

Reviewed

-0.57

POSITIVE LOGITS

estone

0.81

 "$:/

0.75

 totality

0.67

ordinate

0.66

 Appendix

0.65

 chronological

0.64

emort

0.63

anium

0.63

hern

0.62

 liner

0.61

Activations Density 0.190%

instances of the word "included"

phrases that include the word "in" alongside associated contexts or categories

No Comments

No Known Activations