INDEX

Explanations

possessive pronouns followed by an adjective

oai_token-act-pair · gpt-3.5-turbo

variations of the word 'its'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

basketball

-0.80

 Unsure

-0.77

tsy

-0.76

rette

-0.73

stad

-0.72

Gallery

-0.71

ooo

-0.70

pc

-0.68

 Hastings

-0.68

behind

-0.67

POSITIVE LOGITS

own

1.35

ELF

1.22

 predecessor

1.19

 namesake

1.03

 predecessors

1.01

 respective

0.91

 usefulness

0.87

 rightful

0.85

 newest

0.84

 entirety

0.84

Activations Density 0.128%

possessive pronouns followed by an adjective

variations of the word 'its'

No Comments

No Known Activations