INDEX

Explanations

words related to props or objects used in various contexts or scenarios

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "prop" and its variations related to production or usage in a context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Carbuncle

-0.82

DragonMagazine

-0.73

soever

-0.70

lihood

-0.67

hips

-0.66

Interstitial

-0.64

 Peaks

-0.63

tone

-0.62

Maw

-0.62

ppo

-0.61

POSITIVE LOGITS

 prop

1.07

ulsive

0.99

itious

0.99

onents

0.93

hetical

0.90

etry

0.87

hetically

0.87

aganda

0.83

ylene

0.82

uls

0.81

Activations Density 0.007%

words related to props or objects used in various contexts or scenarios

mentions of the word "prop" and its variations related to production or usage in a context

No Comments

No Known Activations