INDEX

Explanations

noun phrases related to technology and software and their components

oai_token-act-pair · gpt-3.5-turbo

expressions indicating relationships between entities or variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

uba

-0.76

zech

-0.71

zek

-0.71

è¦ļéĨĴ

-0.69

azeera

-0.68

arling

-0.66

ynes

-0.66

 spoilers

-0.65

ploy

-0.65

amous

-0.64

POSITIVE LOGITS

which

0.71

PID

0.70

 chaired

0.69

 which

0.67

 wherein

0.66

 comprises

0.65

 Brewers

0.64

ariat

0.62

SPONSORED

0.61

 Drac

0.60

Activations Density 1.034%

noun phrases related to technology and software and their components

expressions indicating relationships between entities or variables

No Comments

No Known Activations