INDEX

Explanations

verbs related to actions or states

oai_token-act-pair · gpt-3.5-turbo

comparisons using the phrase "like."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quad

-0.64

LTD

-0.63

arat

-0.62

 Saud

-0.61

ses

-0.61

ifer

-0.60

 strains

-0.60

reports

-0.60

endant

-0.58

ucci

-0.58

POSITIVE LOGITS

 oneself

1.24

 Yourself

0.76

inventoryQuantity

0.75

rontal

0.72

 yourself

0.69

 Pengu

0.64

veland

0.63

animate

0.61

 immersed

0.61

 mates

0.60

Activations Density 0.510%

verbs related to actions or states

comparisons using the phrase "like."

No Comments

No Known Activations