INDEX

Explanations

terms related to potential uses or applications of a technology or discovery

oai_token-act-pair · gpt-3.5-turbo

references to potential applications and uses of concepts, technologies, or discoveries

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

ignt

-0.77

 Bagg

-0.68

 anten

-0.68

ania

-0.64

irm

-0.63

 PASS

-0.61

owship

-0.61

prep

-0.59

 Rush

-0.59

 Masquerade

-0.59

POSITIVE LOGITS

 applications

0.89

 metaphors

0.81

 usefulness

0.77

Applications

0.77

ationally

0.74

iency

0.70

 versatility

0.70

benefit

0.70

desktop

0.67

Commerce

0.66

Activations Density 0.089%

terms related to potential uses or applications of a technology or discovery

references to potential applications and uses of concepts, technologies, or discoveries

No Comments

No Known Activations