INDEX

Explanations

occurrences of the word 'cart'

oai_token-act-pair · gpt-3.5-turbo

mentions of "cart" or related terms 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ominated

-0.78

 Incarn

-0.75

ispers

-0.69

 Relative

-0.67

posure

-0.66

 Reid

-0.66

 Suicide

-0.66

 Personality

-0.65

 Shutdown

-0.64

idential

-0.64

POSITIVE LOGITS

 cart

4.26

 carts

2.77

cart

2.51

 Cart

2.18

Cart

2.14

 basket

1.26

 wagon

1.17

 buggy

1.04

 wheel

0.95

 stret

0.94

Activations Density 0.013%

occurrences of the word 'cart'

mentions of "cart" or related terms in various contexts

No Comments

No Known Activations