INDEX

Explanations

negative statements expressing inability or lack of action

oai_token-act-pair · gpt-3.5-turbo

phrases expressing inability or lack of action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

obo

-0.68

undrum

-0.67

hat

-0.64

 understatement

-0.63

endi

-0.63

but

-0.62

inventoryQuantity

-0.62

uders

-0.60

udo

-0.60

ructose

-0.60

POSITIVE LOGITS

 conclusive

0.80

 nonetheless

0.80

etheless

0.79

 specifics

0.77

 necessarily

0.68

 enough

0.64

 concrete

0.62

cially

0.62

 definitive

0.61

RESULTS

0.60

Activations Density 0.524%

negative statements expressing inability or lack of action

phrases expressing inability or lack of action

No Comments

No Known Activations