INDEX

Explanations

technical terms related to computer hardware and possibly other technologies

oai_token-act-pair · gpt-3.5-turbo

content related to technical specifications or features of products

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

glers

-0.62

ariat

-0.60

arsh

-0.57

 allowance

-0.56

lik

-0.56

ļéĨĴ

-0.54

conserv

-0.54

 deleg

-0.53

thinkable

-0.53

>.

-0.53

POSITIVE LOGITS

 Released

0.69

 Phant

0.67

 Vulkan

0.66

Offline

0.62

 Revival

0.61

 Neptune

0.61

 Clan

0.61

 Alloy

0.60

 Remix

0.59

 Shin

0.59

Activations Density 0.853%

technical terms related to computer hardware and possibly other technologies

content related to technical specifications or features of products

No Comments

No Known Activations