INDEX

Explanations

technical terms related to hardware and projects

oai_token-act-pair · gpt-3.5-turbo

technical terms and objects related to devices and projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Lank

-0.74

annie

-0.73

ECA

-0.71

azeera

-0.70

 Flavoring

-0.69

 sqor

-0.67

agher

-0.67

ãģĨ

-0.66

 PsyNet

-0.64

soever

-0.64

POSITIVE LOGITS

 itself

1.16

 underwent

0.99

 revolves

0.93

 transitioned

0.92

wright

0.88

 lasted

0.84

 reverted

0.83

 survived

0.83

 succeeded

0.81

 originated

0.81

Activations Density 0.391%

technical terms related to hardware and projects

technical terms and objects related to devices and projects

No Comments

No Known Activations